© 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. 2-RES-SM
    11. 32369
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and operations in code

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    302
    +0.16
    0.9%
    92
    +0.14
    0.8%
    197
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.16
    0.12
    90
    +0.14
    0.11
    45
    +0.13
    0.06
    Negative Logits
     iterator
    -1.63
    ibase
    -1.43
    STM
    -1.41
    wagen
    -1.37
    idation
    -1.35
    idge
    -1.34
    '))
    -1.30
    !)
    -1.29
    arently
    -1.29
    isman
    -1.26
    POSITIVE LOGITS
     age
    1.59
    teenth
    1.56
    }\\
    1.35
    },\\
    1.34
    cht
    1.30
     cov
    1.28
     sag
    1.28
    \":
    1.28
     sexes
    1.28
     adj
    1.25
    Activations Density 4.560%

    No Known Activations