© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27155
    Prev
    Next
    INDEX
    Explanations

    mentions of standard library functions and types in programming contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    369
    +0.21
    1.2%
    466
    +0.15
    0.8%
    233
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.21
    0.03
    415
    +0.15
    0.03
    369
    +0.12
    0.02
    Negative Logits
    ¿½
    -2.12
    ij
    -1.74
    ľĵ
    -1.68
    cretion
    -1.67
    soever
    -1.65
    ·¸
    -1.65
    ¥
    -1.57
    ĥ
    -1.54
    ¨
    -1.54
    Ĥ
    -1.54
    POSITIVE LOGITS
    ::
    1.75
    thouse
    1.67
    ings
    1.67
     (@
    1.57
    works
    1.51
     Comic
    1.43
     speaking
    1.39
    rett
    1.38
    win
    1.36
     autopsy
    1.33
    Activations Density 0.146%

    No Known Activations