© 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. 1-RES-SM
    11. 28256
    Prev
    Next
    INDEX
    Explanations

    words related to choices or alternatives

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.11
    0.6%
    125
    +0.10
    0.6%
    499
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.11
    0.02
    54
    +0.10
    0.02
    280
    +0.10
    0.02
    Negative Logits
    »
    -3.74
    ¦
    -3.56
    ľĵ
    -3.52
    Ĩ
    -3.45
    ĵ
    -3.43
    ĨĴ
    -3.39
    ¢
    -3.32
    ¿
    -3.30
    Ł
    -3.26
    ĩ
    -3.26
    POSITIVE LOGITS
    gio
    1.48
    holds
    1.47
    omorphisms
    1.47
    atype
    1.43
    released
    1.41
    azer
    1.41
    abouts
    1.39
    xico
    1.39
    versible
    1.35
    anian
    1.33
    Activations Density 0.037%

    No Known Activations