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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27187
    Prev
    Next
    INDEX
    Explanations

    terms related to epidemiology

    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
    156
    +0.31
    1.9%
    376
    +0.11
    0.7%
    30
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.31
    0.01
    298
    +0.11
    0.01
    310
    +0.11
    0.01
    Negative Logits
    aded
    -1.52
    ansen
    -1.41
    ows
    -1.36
     declare
    -1.33
    ading
    -1.32
    dered
    -1.30
     plead
    -1.28
     more
    -1.28
    derer
    -1.27
     significantly
    -1.26
    POSITIVE LOGITS
    sheet
    1.71
    etics
    1.64
    istan
    1.62
     standpoint
    1.49
     situation
    1.49
    xture
    1.47
     warfare
    1.46
     contender
    1.45
    iens
    1.41
     relativity
    1.39
    Activations Density 0.056%

    No Known Activations