© 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. 27129
    Prev
    Next
    INDEX
    Explanations

    sections of text that provide detailed descriptions or summaries

    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
    12
    +0.13
    0.7%
    198
    +0.12
    0.7%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.13
    0.01
    232
    +0.12
    0.02
    416
    +0.11
    0.01
    Negative Logits
    %),
    -1.96
    %).
    -1.86
    .),
    -1.78
    .).
    -1.63
    www
    -1.59
      ↵
    -1.57
    ^),
    -1.57
    porter
    -1.56
    Īĺ
    -1.56
    ross
    -1.54
    POSITIVE LOGITS
     Article
    1.56
    continued
    1.49
    irectional
    1.49
     Contin
    1.48
    borough
    1.46
     edition
    1.44
     Classification
    1.42
    ication
    1.41
    itious
    1.40
    smen
    1.40
    Activations Density 0.034%

    No Known Activations