© 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. 28270
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and court procedures

    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
    +0.25
    1.5%
    234
    +0.15
    0.9%
    197
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    234
    +0.25
    0.11
    186
    +0.15
    -0.03
    187
    +0.12
    0.08
    Negative Logits
    >';
    -1.52
     conjugation
    -1.52
     '</
    -1.51
    jection
    -1.45
     factorization
    -1.44
     clamp
    -1.44
    jours
    -1.43
     functor
    -1.42
     Eqs
    -1.42
    )|^
    -1.40
    POSITIVE LOGITS
    +.
    1.78
    .
    1.78
    ")]
    1.69
    naire
    1.65
    .")
    1.62
     than
    1.61
    innati
    1.61
    liga
    1.61
    ").
    1.61
    "].
    1.57
    Activations Density 3.123%

    No Known Activations