© 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 EvalsExportsAPI 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. 13016
    Prev
    Next
    INDEX
    Explanations

    import statements in programming code

    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
    78
    +0.21
    1.3%
    21
    +0.21
    1.3%
    397
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.21
    0.03
    123
    +0.21
    0.04
    21
    +0.16
    0.02
    Negative Logits
    ,’
    -2.26
    ’,
    -1.83
    .’
    -1.81
    ’.
    -1.73
    .’”
    -1.70
     towards
    -1.63
    ?’
    -1.60
    ,'
    -1.51
    ,”
    -1.51
    ’
    -1.43
    POSITIVE LOGITS
    ŀ
    2.58
    ©
    2.48
    į
    2.44
    Ĭ
    2.42
    Ķ
    2.38
    ĩ
    2.29
    °
    2.28
    IJ
    2.26
    «
    2.24
    ¡
    2.23
    Activations Density 0.121%

    No Known Activations