© 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. 29543
    Prev
    Next
    INDEX
    Explanations

    expressions of questioning or inquiry, particularly those starting with "how."

    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
    497
    +0.14
    0.8%
    473
    +0.12
    0.7%
    175
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.44
    98
    +0.12
    0.19
    23
    +0.12
    0.32
    Negative Logits
    printStackTrace
    -1.67
    ¹
    -1.64
    İ
    -1.62
    ħ
    -1.60
    abi
    -1.56
    ¤
    -1.52
    ģ
    -1.47
    ĥ
    -1.45
     notch
    -1.42
    shaw
    -1.42
    POSITIVE LOGITS
    ETHOD
    1.93
    essee
    1.56
    MENT
    1.46
    AGE
    1.39
    uries
    1.39
    ions
    1.36
    itudes
    1.36
     solutions
    1.35
    idegger
    1.35
     melanoma
    1.30
    Activations Density 3.133%

    No Known Activations