© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15138
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and software applications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    476
    +0.14
    0.8%
    25
    +0.13
    0.8%
    95
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.14
    0.04
    146
    +0.13
    0.05
    177
    +0.13
    0.04
    Negative Logits
    ĵ
    -2.69
    ´
    -2.46
    Ĭ
    -2.44
    IJ
    -2.40
    ·¸
    -2.39
    ·
    -2.31
    ĥ½
    -2.23
    ¨
    -2.18
    ¸
    -2.17
    ĩ
    -2.15
    POSITIVE LOGITS
    ://
    2.33
     explorer
    2.20
    client
    2.08
    rc
    2.06
    odb
    1.95
    js
    1.94
    ctl
    1.93
     firefox
    1.90
    cmd
    1.88
    fiddle
    1.87
    Activations Density 0.268%

    No Known Activations