© 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. 30019
    Prev
    Next
    INDEX
    Explanations

    mentions of the character "b"

    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
    383
    +0.12
    0.7%
    394
    +0.12
    0.6%
    360
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.12
    0.00
    10
    +0.12
    0.00
    164
    +0.11
    0.00
    Negative Logits
     whom
    -1.67
     Congress
    -1.66
    estation
    -1.64
    ished
    -1.63
     -,
    -1.60
    eln
    -1.53
    ivities
    -1.52
    ération
    -1.46
     merit
    -1.45
    eton
    -1.45
    POSITIVE LOGITS
    cock
    1.65
    core
    1.54
    parametric
    1.46
    tochrome
    1.45
    AND
    1.44
    schemas
    1.42
    cores
    1.42
    addle
    1.42
    added
    1.39
    riction
    1.37
    Activations Density 0.001%

    No Known Activations