© 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. 32380
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and operations related to data handling

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    293
    +0.23
    1.3%
    400
    +0.15
    0.9%
    237
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.20
    156
    +0.15
    0.22
    71
    +0.12
    0.21
    Negative Logits
    ↵            ↵
    -1.59
       ↵
    -1.59
    -1.59
    č↵
    -1.59
    -1.59
    <|outofrange|>
    -1.59
    -1.59
    -1.59
    <|padding|>
    -1.59
    -1.59
    POSITIVE LOGITS
    ifice
    1.53
    >()
    1.44
    illary
    1.40
    ligt
    1.39
    ();
    1.35
    BOOL
    1.35
    ishment
    1.35
    throw
    1.35
    DOCTYPE
    1.35
    stance
    1.34
    Activations Density 4.615%

    No Known Activations