© 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. 26065
    Prev
    Next
    INDEX
    Explanations

    terms related to local context or locality

    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
    156
    +0.19
    1.1%
    476
    +0.11
    0.6%
    404
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.19
    0.01
    476
    +0.11
    0.01
    404
    +0.10
    0.01
    Negative Logits
    ĥ
    -2.02
    fully
    -1.91
    Ĥ¬
    -1.85
    Į
    -1.74
    ĥ½
    -1.73
    ful
    -1.61
    acity
    -1.56
    <|outofrange|>
    -1.54
    -1.54
    ↵↵
    -1.54
    POSITIVE LOGITS
    ached
    1.59
    mie
    1.49
    aeda
    1.48
     supra
    1.43
     Xi
    1.40
    quier
    1.36
     extinct
    1.32
    iei
    1.31
    \$
    1.30
    ista
    1.29
    Activations Density 0.054%

    No Known Activations