© 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. 2-RES-SM
    11. 13349
    Prev
    Next
    INDEX
    Explanations

    questions about programming, specifically related to functions or methods

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    159
    +0.15
    0.8%
    23
    +0.14
    0.8%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.15
    0.03
    431
    +0.14
    0.02
    438
    +0.14
    0.03
    Negative Logits
    ancer
    -1.83
    enti
    -1.70
    ľĵ
    -1.69
    »¿
    -1.66
    ifice
    -1.66
     controls
    -1.66
    ¿
    -1.64
    ĸ
    -1.63
    ¼
    -1.63
    Ļ
    -1.60
    POSITIVE LOGITS
    apine
    1.47
     regards
    1.45
     sure
    1.42
    Decided
    1.41
     First
    1.38
    thanks
    1.37
    ------------------------------------------------------
    1.36
    ounded
    1.36
     pregnant
    1.35
    Something
    1.35
    Activations Density 0.090%

    No Known Activations