© 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. 26376
    Prev
    Next
    INDEX
    Explanations

    occurrences of namespaces in code

    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
    79
    +0.12
    0.6%
    383
    +0.11
    0.6%
    55
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.12
    0.02
    79
    +0.11
    0.02
    383
    +0.11
    0.02
    Negative Logits
    ?).
    -1.72
    ptin
    -1.65
    ?)
    -1.56
     figure
    -1.54
    ?"
    -1.42
    print
    -1.40
     part
    -1.38
     occurs
    -1.38
    ^[@
    -1.38
    ?,
    -1.37
    POSITIVE LOGITS
    <|outofrange|>
    3.51
    3.51
    č↵
    3.51
    3.51
    <|outofrange|>
    3.51
    3.51
    ↵↵
    3.51
    3.51
    ↵
    3.51
    ↵
    3.51
    Activations Density 0.050%

    No Known Activations