© 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. 25520
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and court cases

    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
    351
    +0.15
    0.8%
    444
    +0.11
    0.6%
    100
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.15
    0.02
    108
    +0.11
    0.02
    72
    +0.11
    0.02
    Negative Logits
    âĢ¯
    -1.73
    dex
    -1.72
    ty
    -1.68
    fen
    -1.66
    nia
    -1.58
    npmjs
    -1.57
    nie
    -1.56
    uka
    -1.54
    uly
    -1.53
    (**
    -1.53
    POSITIVE LOGITS
    INGS
    1.73
    aries
    1.65
    alls
    1.57
    ALE
    1.54
     course
    1.54
    sight
    1.50
    lasses
    1.49
     stars
    1.46
     Rangers
    1.45
     circles
    1.45
    Activations Density 0.133%

    No Known Activations