© 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. 1-RES-SM
    11. 23940
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to imprisonment and the criminal justice system

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    290
    +0.12
    0.7%
    355
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.19
    0.03
    111
    +0.12
    0.03
    290
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.17
    Ŀ
    -2.61
    Į
    -2.56
    Ķ
    -2.54
    ¯
    -2.50
    °
    -2.48
    ¨
    -2.45
    ¹
    -2.44
    ¾
    -2.44
    ĭ
    -2.43
    POSITIVE LOGITS
    break
    2.17
    nier
    1.93
    yard
    1.80
    izumab
    1.63
     eligibility
    1.60
    station
    1.58
    oque
    1.55
     (§
    1.53
     commiss
    1.53
    ctions
    1.52
    Activations Density 0.281%

    No Known Activations