© 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. 4-RES-SM
    11. 11650
    Prev
    Next
    INDEX
    Explanations

    code annotations and documentation comments

    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
    36
    +0.15
    0.8%
    38
    +0.15
    0.8%
    182
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.15
    0.04
    36
    +0.15
    0.04
    422
    +0.14
    0.04
    Negative Logits
     longer
    -1.69
    ier
    -1.68
    omers
    -1.54
    ptin
    -1.53
    arter
    -1.52
    inned
    -1.50
     older
    -1.46
     surviving
    -1.42
    osis
    -1.41
    phia
    -1.41
    POSITIVE LOGITS
    İ
    3.77
    IJ
    3.63
    ļ
    3.61
    ľĵ
    3.61
    ¼
    3.58
    Ķ
    3.49
    Ĥ
    3.42
    Ń
    3.38
    Į
    3.33
    ·
    3.31
    Activations Density 0.103%

    No Known Activations