© 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. 1-RES-SM
    11. 26357
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics

    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
    408
    +0.13
    0.7%
    100
    +0.11
    0.6%
    21
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.13
    0.06
    286
    +0.11
    0.05
    88
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -1.95
    ī
    -1.77
    ĥ½
    -1.56
    Īĺ
    -1.55
     ).
    -1.54
    Ĥ
    -1.51
    unnumbered
    -1.50
    utting
    -1.45
    ivity
    -1.45
    asting
    -1.45
    POSITIVE LOGITS
    naire
    1.61
    ÅĽÄĩ
    1.57
    anese
    1.57
     jobs
    1.51
     firefighters
    1.48
     concerts
    1.48
    gres
    1.46
    %"
    1.46
    hire
    1.46
    iors
    1.45
    Activations Density 0.084%

    No Known Activations