© 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. 4-RES-SM
    11. 14810
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in code snippets

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    397
    +0.32
    2.0%
    78
    +0.19
    1.2%
    466
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.32
    0.07
    57
    +0.19
    0.06
    52
    +0.13
    0.05
    Negative Logits
    ially
    -1.69
    icine
    -1.68
    uty
    -1.57
    icals
    -1.49
     dehydrogenase
    -1.46
    enic
    -1.46
    actin
    -1.46
    irubin
    -1.45
    illin
    -1.40
    oxacin
    -1.39
    POSITIVE LOGITS
    ¥
    4.57
    ¦
    4.46
      ↵
    4.38
    ↵↵
    4.38
    <|outofrange|>
    4.38
    ↵↵
    4.38
    <|outofrange|>
    4.38
    <|outofrange|>
    4.38
    ↵            ↵
    4.38
    ↵↵↵
    4.38
    Activations Density 0.159%

    No Known Activations