© 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. 30025
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "values" in various contexts

    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
    +0.21
    1.2%
    54
    +0.13
    0.7%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.21
    0.02
    77
    +0.13
    0.02
    60
    +0.12
    0.02
    Negative Logits
    -4.49
    -4.49
    ↵
    -4.49
    č↵
    -4.49
    -4.49
    <|outofrange|>
    -4.49
    ↵↵
    -4.49
    -4.49
    -4.49
     ↵
    -4.49
    POSITIVE LOGITS
    etting
    1.97
    hell
    1.83
    pace
    1.77
    mith
    1.76
    heet
    1.71
    cript
    1.62
     contained
    1.59
    igner
    1.53
    PEC
    1.52
    ign
    1.51
    Activations Density 0.041%

    No Known Activations