Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27044
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the substring "ch."

    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
    369
    +0.22
    1.3%
    410
    +0.16
    0.9%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.22
    0.03
    172
    +0.16
    0.02
    201
    +0.12
    0.03
    Negative Logits
    ļ
    -2.78
    ¢
    -2.63
    Ĥ
    -2.55
    ľ
    -2.53
    ĩ
    -2.52
    »¿
    -2.48
    į
    -2.47
    ĸ
    -2.47
    ¡
    -2.38
    İ
    -2.37
    POSITIVE LOGITS
    icago
    1.72
    rooms
    1.68
    ismatic
    1.61
     induct
    1.61
    neys
    1.54
     concluded
    1.50
     averaged
    1.44
     expressed
    1.43
    otype
    1.39
    iele
    1.37
    Activations Density 0.041%

    No Known Activations