© 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. 2-RES-SM
    11. 32253
    Prev
    Next
    INDEX
    Explanations

    key sporting statistics and individual performances

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    96
    +0.12
    0.6%
    368
    +0.10
    0.6%
    111
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.12
    0.09
    319
    +0.10
    0.05
    368
    +0.10
    0.04
    Negative Logits
    ij
    -2.61
    Ĵ
    -2.47
    č↵
    -2.45
    -2.45
    -2.45
    ↵
    -2.45
    ↵↵
    -2.45
     ↵
    -2.45
    <|outofrange|>
    -2.45
    -2.45
    POSITIVE LOGITS
    innings
    2.16
     season
    1.96
     Championships
    1.88
     leagues
    1.83
     championships
    1.83
     Players
    1.80
    ership
    1.78
    Players
    1.78
    ansas
    1.77
     Finals
    1.77
    Activations Density 1.259%

    No Known Activations