© 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. 10358
    Prev
    Next
    INDEX
    Explanations

    words related to legal outcomes and 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/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
    156
    +0.33
    2.1%
    21
    +0.17
    1.1%
    478
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.33
    0.14
    291
    +0.17
    0.10
    145
    +0.16
    0.09
    Negative Logits
    rome
    -1.71
    enstein
    -1.58
     solved
    -1.53
     arte
    -1.45
     (,
    -1.43
    idian
    -1.37
    Ãħ
    -1.35
     builds
    -1.35
    ality
    -1.34
     describes
    -1.34
    POSITIVE LOGITS
     foregoing
    2.63
     Honorable
    2.10
    odor
    2.04
     entirety
    1.98
     parties
    1.96
     facts
    1.94
     Secretary
    1.93
     appellants
    1.93
     plaintiffs
    1.91
     aforementioned
    1.88
    Activations Density 0.974%

    No Known Activations