© 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. 30886
    Prev
    Next
    INDEX
    Explanations

    references to "cable" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.14
    0.9%
    113
    +0.13
    0.8%
    156
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.02
    429
    +0.13
    0.02
    453
    +0.11
    0.01
    Negative Logits
     spontaneous
    -1.70
     pleasure
    -1.61
     dramatic
    -1.58
     happier
    -1.55
     sexual
    -1.54
     place
    -1.53
     brutal
    -1.52
     entire
    -1.50
     unwanted
    -1.48
     fancy
    -1.47
    POSITIVE LOGITS
    erie
    1.93
    ipers
    1.93
    itud
    1.88
    ģ
    1.78
    tees
    1.76
    eners
    1.76
    tee
    1.74
    watson
    1.72
    caster
    1.67
    worth
    1.65
    Activations Density 0.011%

    No Known Activations