© 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. Residuals
    9. 4-RES-SM
    11. 13458
    Prev
    Next
    INDEX
    Explanations

    biochemical processes and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    47
    +0.11
    0.6%
    211
    +0.11
    0.6%
    153
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.11
    0.03
    211
    +0.11
    0.04
    177
    +0.11
    0.04
    Negative Logits
    »¿
    -3.46
    ľĵ
    -3.12
    ¿
    -2.96
    Ĥ¬
    -2.95
    ¿½
    -2.91
    ²
    -2.86
    ¹
    -2.82
    ↵
    -2.82
    -2.82
              ↵
    -2.82
    POSITIVE LOGITS
     kinetics
    2.83
     rate
    2.63
     reactions
    2.50
     process
    2.50
     rates
    2.49
     occurring
    2.33
     reaction
    2.32
     processes
    2.31
     phenomena
    2.30
     efficiencies
    2.26
    Activations Density 0.250%

    No Known Activations