© 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. 29916
    Prev
    Next
    INDEX
    Explanations

    variations of the word "fit" in various contexts related to compatibility or suitability

    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
    376
    +0.17
    0.9%
    118
    +0.13
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.17
    0.02
    380
    +0.13
    0.02
    118
    +0.12
    0.03
    Negative Logits
    ·
    -2.45
    ¾
    -2.37
    ¨
    -2.37
    ®
    -2.17
    ĺ
    -2.16
    Ĺ
    -2.13
    ±
    -2.12
    ´
    -2.09
    ¶
    -2.03
    µ
    -2.02
    POSITIVE LOGITS
    ters
    2.10
    IBILITY
    1.85
    iest
    1.67
    ibly
    1.66
    ible
    1.64
    ibular
    1.64
    rier
    1.64
    gerald
    1.63
    ably
    1.63
    lasses
    1.60
    Activations Density 0.182%

    No Known Activations