© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23804
    Prev
    Next
    INDEX
    Explanations

    terms related to user registration and navigation in a forum context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    26
    +0.13
    0.7%
    379
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.13
    0.04
    26
    +0.12
    0.02
    288
    +0.11
    0.03
    Negative Logits
    ĥ
    -3.05
    Ķ
    -2.54
    Ĭ
    -2.53
    Ŀ
    -2.53
    ↵            ↵
    -2.45
    -2.45
    -2.45
               ↵
    -2.45
    <|outofrange|>
    -2.45
    č↵
    -2.45
    POSITIVE LOGITS
     blogs
    1.88
    xico
    1.82
     YOU
    1.77
    blogs
    1.72
     email
    1.67
     blog
    1.63
    ncbi
    1.60
     NOT
    1.58
    ureus
    1.54
     SEO
    1.52
    Activations Density 0.423%

    No Known Activations