© 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. MLP Post
    9. 0-MLP-SM
    11. 26400
    Prev
    Next
    INDEX
    Explanations

    references to "OCK" and "SOCK," likely related to specific coding conventions or keywords in a programming context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    394
    +0.13
    0.8%
    129
    +0.12
    0.7%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.13
    0.01
    70
    +0.12
    0.01
    276
    +0.12
    0.01
    Negative Logits
     slightest
    -1.63
     '</
    -1.51
     cry
    -1.41
     fair
    -1.39
     concerned
    -1.37
    duction
    -1.36
     consequence
    -1.35
     complete
    -1.34
    hem
    -1.34
    fection
    -1.33
    POSITIVE LOGITS
    istical
    1.85
    esto
    1.74
    ingly
    1.65
    enstein
    1.63
    culus
    1.63
    ymb
    1.63
    pool
    1.63
    worthy
    1.62
    ist
    1.61
    iewicz
    1.60
    Activations Density 0.024%

    No Known Activations