© 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. 27752
    Prev
    Next
    INDEX
    Explanations

    references to the word "Rom" or related terms

    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
    410
    +0.15
    0.9%
    332
    +0.13
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.15
    0.02
    410
    +0.13
    0.01
    285
    +0.13
    0.01
    Negative Logits
    rapeut
    -2.10
     supporting
    -1.49
    ctica
    -1.44
     warning
    -1.43
     investigating
    -1.42
     signs
    -1.41
     Investig
    -1.40
     facts
    -1.40
     reper
    -1.40
    uties
    -1.38
    POSITIVE LOGITS
    pton
    1.89
    ouin
    1.89
     µL
    1.69
    uet
    1.67
    uel
    1.60
    ikel
    1.57
    ping
    1.48
    imoto
    1.47
    gae
    1.47
    ilee
    1.46
    Activations Density 0.038%

    No Known Activations