© 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. 29472
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Forward."

    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
    464
    +0.13
    0.7%
    298
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.12
    271
    +0.12
    0.04
    156
    +0.11
    0.06
    Negative Logits
    bund
    -1.78
    vir
    -1.63
    than
    -1.62
     detriment
    -1.58
     respectively
    -1.48
    osa
    -1.42
    vard
    -1.41
    STER
    -1.39
    stock
    -1.37
    aster
    -1.37
    POSITIVE LOGITS
     wondering
    1.52
     comments
    1.51
    uego
    1.50
    questions
    1.45
     yours
    1.40
     Comments
    1.39
    ÃŃc
    1.38
    à¸ĩ
    1.34
     legs
    1.33
     grabs
    1.33
    Activations Density 0.216%

    No Known Activations