© 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. 29686
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and."

    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
    164
    +0.14
    0.8%
    393
    +0.13
    0.7%
    53
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.05
    389
    +0.13
    0.04
    314
    +0.13
    0.04
    Negative Logits
    irs
    -1.82
     boys
    -1.71
     girls
    -1.67
     answer
    -1.64
     rooms
    -1.61
    isms
    -1.56
     guys
    -1.56
    rens
    -1.56
    ress
    -1.55
     streets
    -1.53
    POSITIVE LOGITS
    Ķ
    2.50
    Ĥ¬
    2.47
    ļ
    2.44
    ®
    2.44
    °
    2.38
    ī
    2.34
    ↵
    2.33
    <|padding|>
    2.33
    ↵
    2.33
    2.33
    Activations Density 0.035%

    No Known Activations