© 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 EvalsExportsAPI 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. 28062
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences

    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
    23
    +0.14
    0.8%
    435
    +0.12
    0.6%
    41
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    271
    +0.12
    0.02
    156
    +0.12
    0.02
    Negative Logits
    sy
    -1.80
    ings
    -1.72
    zes
    -1.59
    ĥ½
    -1.53
    legraph
    -1.47
    illion
    -1.41
    breaking
    -1.36
    mill
    -1.34
    Ł
    -1.31
    æ
    -1.31
    POSITIVE LOGITS
    ITC
    1.55
     Cauc
    1.54
    kins
    1.50
     Correct
    1.42
     Spa
    1.37
    formed
    1.35
     Northeast
    1.33
    iven
    1.32
     Midwest
    1.31
    ypse
    1.31
    Activations Density 0.006%

    No Known Activations