© 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. 4-RES-SM
    11. 8909
    Prev
    Next
    INDEX
    Explanations

    references to script sources in HTML code

    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
    74
    +0.13
    0.7%
    78
    +0.12
    0.7%
    255
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.13
    0.02
    74
    +0.12
    0.02
    244
    +0.11
    0.02
    Negative Logits
    thon
    -1.47
     bills
    -1.44
     ordinary
    -1.43
     losses
    -1.43
     incumbent
    -1.43
     Insurance
    -1.32
     Gardens
    -1.31
    olis
    -1.31
     Aff
    -1.30
    iber
    -1.30
    POSITIVE LOGITS
    ³
    4.45
    ©
    4.36
    ij
    4.33
    ŀ
    4.33
    ¼
    4.29
    ¦
    4.28
    ĨĴ
    4.21
    ¢
    4.17
    §
    4.16
    £
    4.08
    Activations Density 0.071%

    No Known Activations