© 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. 1-RES-SM
    11. 28438
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal actions or proceedings, specifically appeals and judicial judgments

    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
    478
    +0.17
    1.0%
    74
    +0.15
    0.9%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.17
    0.03
    74
    +0.15
    0.02
    52
    +0.13
    0.01
    Negative Logits
    "}](
    -1.67
    rome
    -1.49
    illin
    -1.47
    }",
    -1.42
    )",
    -1.40
    needed
    -1.40
     ball
    -1.39
    aden
    -1.39
    ÃŃs
    -1.38
     needed
    -1.37
    POSITIVE LOGITS
    Ļª
    3.36
    ĻĤ
    3.29
    ŀ
    3.16
    Į
    3.13
    »¿
    3.04
    Ī
    3.02
    ¿½
    3.01
    ľĵ
    2.99
    µ
    2.99
    ĵ
    2.93
    Activations Density 0.143%

    No Known Activations