© 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. 15196
    Prev
    Next
    INDEX
    Explanations

    details related to job responsibilities and technical qualifications within a professional 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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.31
    1.9%
    240
    +0.12
    0.7%
    246
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.31
    0.07
    481
    +0.12
    0.09
    450
    +0.11
    0.01
    Negative Logits
    ↵
    -2.45
    -2.45
    -2.45
    -2.45
    ↵↵
    -2.45
    -2.45
    ↵
    -2.45
    ↵        ↵
    -2.45
    -2.45
    <|outofrange|>
    -2.45
    POSITIVE LOGITS
    âĢ¢
    2.00
     Participants
    1.65
    ”
    1.64
     Cognitive
    1.63
    ”)
    1.63
    autions
    1.62
    whether
    1.62
    iplinary
    1.61
    oneliness
    1.54
    Educ
    1.54
    Activations Density 1.488%

    No Known Activations