© 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. 4-RES-SM
    11. 13699
    Prev
    Next
    INDEX
    Explanations

    data related to clinical trial results and genetic research

    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
    369
    +0.14
    0.8%
    350
    +0.13
    0.8%
    348
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.03
    350
    +0.13
    0.04
    72
    +0.13
    0.03
    Negative Logits
    ĻĤ
    -1.80
    ij
    -1.60
     detail
    -1.52
    ĨĴ
    -1.48
    Ĥ¬
    -1.48
    words
    -1.43
    reason
    -1.42
     explain
    -1.41
     details
    -1.41
    ¢
    -1.38
    POSITIVE LOGITS
    orf
    1.75
    kDa
    1.73
    +.
    1.67
    LLOW
    1.65
    omonas
    1.60
    psilon
    1.57
    idase
    1.56
    chst
    1.55
     mutant
    1.55
    osyl
    1.55
    Activations Density 0.229%

    No Known Activations