© 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. 4-RES-SM
    11. 8752
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data structures

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    397
    +0.15
    0.8%
    320
    +0.14
    0.8%
    9
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.15
    0.09
    9
    +0.14
    0.06
    78
    +0.13
    0.00
    Negative Logits
    ACH
    -1.59
    herin
    -1.59
    Reviewer
    -1.51
     masters
    -1.42
    holds
    -1.38
    DCs
    -1.38
    HO
    -1.37
    aliana
    -1.36
    hele
    -1.34
    ^*$
    -1.34
    POSITIVE LOGITS
     int
    3.42
    int
    2.87
     float
    2.75
     bool
    2.41
     integer
    2.38
     boolean
    2.30
     unsigned
    2.26
     double
    2.24
     char
    2.21
     long
    2.13
    Activations Density 0.743%

    No Known Activations