© 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. 26450
    Prev
    Next
    INDEX
    Explanations

    conjunctions that introduce additional information or context

    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
    129
    +0.17
    1.0%
    23
    +0.12
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.17
    0.01
    300
    +0.12
    0.01
    155
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.91
    º
    -2.83
    Ĥ¬
    -2.73
    ģ
    -2.71
    ĨĴ
    -2.58
    ĥ
    -2.56
    Ļª
    -2.55
    ĩ
    -2.52
    ļ
    -2.36
    Īĺ
    -2.33
    POSITIVE LOGITS
    fection
    1.64
    remia
    1.58
    medium
    1.46
     showing
    1.44
    caption
    1.41
    exists
    1.40
    between
    1.38
    ury
    1.37
    yses
    1.37
     narrowing
    1.36
    Activations Density 0.009%

    No Known Activations