© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    programming and coding constructs, particularly those related to functions and variable assignments

    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
    38
    +0.13
    0.7%
    397
    +0.13
    0.7%
    63
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.13
    0.00
    290
    +0.13
    0.01
    397
    +0.11
    0.01
    Negative Logits
    roph
    -1.79
    zzles
    -1.76
    bles
    -1.67
    reich
    -1.66
     waived
    -1.58
    umen
    -1.57
     belonged
    -1.53
    rives
    -1.53
    coins
    -1.51
     trademarks
    -1.48
    POSITIVE LOGITS
    į
    4.51
    ®
    4.42
    ©
    4.37
    ¥
    4.25
    ¡
    4.22
    Ķ
    4.19
    ŀ
    4.18
    ½
    4.13
    İ
    4.11
    ·¸
    4.08
    Activations Density 0.100%

    No Known Activations