© 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 EvalsExportsAPI 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. 28671
    Prev
    Next
    INDEX
    Explanations

    references to muscle and muscularity

    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
    +0.13
    0.8%
    377
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.01
    104
    +0.13
    0.01
    99
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -1.75
    woke
    -1.75
    hes
    -1.54
    llll
    -1.54
     suicide
    -1.53
    lı
    -1.42
     same
    -1.41
    Č
    -1.41
    rapeut
    -1.40
    ÑĢоÑģ
    -1.40
    POSITIVE LOGITS
    istor
    1.64
    notes
    1.60
    aments
    1.56
    istors
    1.54
    ist
    1.52
    builder
    1.50
    casts
    1.49
     specs
    1.48
    imeters
    1.47
    istry
    1.47
    Activations Density 0.007%

    No Known Activations