© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29809
    Prev
    Next
    INDEX
    Explanations

    references to legal processes or regulations

    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
    269
    +0.17
    0.9%
    367
    +0.11
    0.6%
    347
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.17
    0.39
    53
    +0.11
    0.41
    56
    +0.11
    0.11
    Negative Logits
    ){#
    -1.93
    duced
    -1.65
    ferent
    -1.55
     both
    -1.53
    ken
    -1.49
     investigate
    -1.47
    ressed
    -1.42
    bler
    -1.39
     control
    -1.35
     address
    -1.35
    POSITIVE LOGITS
    hole
    1.60
    fing
    1.53
    imab
    1.52
     fibrillation
    1.48
    works
    1.47
    ITERATION
    1.46
     arrangements
    1.40
    card
    1.37
    ERY
    1.36
    jets
    1.35
    Activations Density 7.528%

    No Known Activations