© 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. 25473
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Res" and its variants, indicating a focus on resilience or resourcefulness

    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
    192
    +0.11
    0.6%
    402
    +0.11
    0.6%
    25
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.08
    156
    +0.11
    0.04
    271
    +0.10
    0.03
    Negative Logits
    lasses
    -1.75
    ering
    -1.67
    rer
    -1.64
    osine
    -1.63
    esis
    -1.55
    ération
    -1.52
     wonders
    -1.49
    iasis
    -1.49
    asma
    -1.48
     excess
    -1.48
    POSITIVE LOGITS
    ĺ
    2.02
    idents
    1.97
    igned
    1.86
    idency
    1.75
    ¡
    1.73
    pective
    1.73
    pected
    1.71
    olved
    1.70
    ĻĤ
    1.70
    ³
    1.66
    Activations Density 0.417%

    No Known Activations