© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15306
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to family court proceedings and parental rights

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.26
    1.5%
    78
    +0.19
    1.1%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.26
    0.02
    441
    +0.19
    0.00
    438
    +0.12
    0.01
    Negative Logits
    iny
    -1.60
    pad
    -1.49
    igen
    -1.44
    water
    -1.43
    omycin
    -1.43
    zing
    -1.43
    gers
    -1.39
    ger
    -1.38
    igt
    -1.37
    izing
    -1.36
    POSITIVE LOGITS
    AFFIRMED
    2.42
    Ī
    2.23
     Honorable
    1.99
    Affirmed
    1.86
    Ķ
    1.82
    ²
    1.82
    Ģ
    1.78
    Appeal
    1.64
    ORDER
    1.63
    }_{-
    1.60
    Activations Density 0.059%

    No Known Activations