© 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. 29905
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical interactions and programming functions 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/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
    430
    +0.13
    0.7%
    450
    +0.11
    0.6%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.10
    486
    +0.11
    0.08
    98
    +0.11
    -0.04
    Negative Logits
    ATCH
    -1.54
    ighs
    -1.51
    INGS
    -1.39
    defer
    -1.35
    orea
    -1.35
    och
    -1.35
    ODU
    -1.34
     msgid
    -1.32
    OVER
    -1.31
    kte
    -1.31
    POSITIVE LOGITS
     again
    1.78
    etting
    1.77
    ño
    1.72
    /-/
    1.69
     himself
    1.68
    taire
    1.65
     itself
    1.64
    ment
    1.63
    ity
    1.61
    nement
    1.60
    Activations Density 1.855%

    No Known Activations