Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27324
    Prev
    Next
    INDEX
    Explanations

    references to wrestling and combat sports

    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
    128
    +0.13
    0.7%
    424
    +0.12
    0.7%
    460
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.13
    0.01
    128
    +0.12
    0.01
    429
    +0.12
    0.01
    Negative Logits
    ago
    -1.73
    zes
    -1.51
    aging
    -1.49
    orie
    -1.48
    utt
    -1.47
     reviewing
    -1.40
     bowel
    -1.40
    anus
    -1.40
    quiry
    -1.38
    agers
    -1.36
    POSITIVE LOGITS
    nuts
    2.06
    doms
    1.95
    )|$(
    1.75
    hurst
    1.68
    nut
    1.63
    place
    1.58
    pole
    1.55
    gered
    1.53
    à°¿
    1.51
     temples
    1.51
    Activations Density 0.025%

    No Known Activations