© 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. 4-RES-SM
    11. 10679
    Prev
    Next
    INDEX
    Explanations

    numerical references to legal cases or statutes

    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
    21
    +0.31
    2.0%
    78
    +0.17
    1.1%
    362
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.31
    0.05
    216
    +0.17
    0.05
    318
    +0.13
    0.04
    Negative Logits
     crowd
    -1.31
     manually
    -1.29
     stored
    -1.27
     bins
    -1.27
    ters
    -1.27
     bin
    -1.26
     sized
    -1.26
     kingdom
    -1.25
    oelectric
    -1.25
    ibility
    -1.24
    POSITIVE LOGITS
    AFFIRMED
    1.92
    UNITED
    1.63
    ¶
    1.54
    )))**
    1.53
    ))/(-
    1.49
    )|^
    1.46
    ))/((-
    1.46
    ))).
    1.45
     ("[
    1.44
     APPEALS
    1.40
    Activations Density 0.143%

    No Known Activations