© 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. 2-RES-SM
    11. 26169
    Prev
    Next
    INDEX
    Explanations

    instances of certain phrases and similar patterns in legal or technical documents

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    254
    +0.14
    0.8%
    478
    +0.14
    0.8%
    61
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.14
    0.01
    427
    +0.14
    0.01
    364
    +0.13
    0.01
    Negative Logits
     ($
    -1.58
    pany
    -1.57
    cursors
    -1.55
     matching
    -1.52
     database
    -1.49
     (£
    -1.48
     placeholder
    -1.47
     analyzer
    -1.44
     vs
    -1.41
     hasht
    -1.40
    POSITIVE LOGITS
    ©
    2.21
    §
    1.86
    liness
    1.76
    Ĭ
    1.75
    ĥ½
    1.73
    "?"
    1.65
     respects
    1.61
    Ī
    1.55
    Ķ
    1.55
    İ
    1.55
    Activations Density 0.027%

    No Known Activations