© 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. 25099
    Prev
    Next
    INDEX
    Explanations

    terms associated with bankruptcy and legal issues

    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
    156
    +0.20
    1.2%
    271
    +0.15
    0.9%
    93
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.20
    0.01
    156
    +0.15
    0.01
    271
    +0.11
    -0.00
    Negative Logits
    dule
    -1.71
    empre
    -1.70
    sell
    -1.65
    leans
    -1.63
    unnumbered
    -1.60
    jours
    -1.54
    ĥ½
    -1.54
     Acad
    -1.46
    ============
    -1.46
    llll
    -1.44
    POSITIVE LOGITS
     itself
    1.65
     chamber
    1.60
     stem
    1.56
    ism
    1.55
    ogenic
    1.54
     inducible
    1.52
     inside
    1.52
     detection
    1.52
    resis
    1.51
     regulator
    1.48
    Activations Density 0.031%

    No Known Activations