© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30392
    Prev
    Next
    INDEX
    Explanations

    the word "hence" in various contexts, indicating a conclusion or result

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.19
    1.1%
    103
    +0.15
    0.8%
    472
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.19
    0.01
    104
    +0.15
    0.01
    425
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.78
    ible
    -1.71
    antly
    -1.50
    --------------------------------------------------------------------------------------------------------------------------------
    -1.50
    ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    -1.47
    ificantly
    -1.44
    º
    -1.40
    ļ
    -1.38
    ![**
    -1.35
    ĸ
    -1.34
    POSITIVE LOGITS
    forth
    2.14
    thon
    2.01
    gium
    1.63
    iosis
    1.54
    jection
    1.49
    óg
    1.44
    kins
    1.43
    chitz
    1.42
    forward
    1.39
    mania
    1.39
    Activations Density 0.226%

    No Known Activations