© 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. 26460
    Prev
    Next
    INDEX
    Explanations

    the pronoun "he" in various contexts

    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
    354
    +0.13
    0.7%
    301
    +0.12
    0.6%
    134
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.13
    0.11
    248
    +0.12
    0.09
    295
    +0.11
    0.09
    Negative Logits
    Ĭ
    -2.13
    µ
    -2.12
    Īĺ
    -2.05
    ļ
    -2.05
    ¨
    -2.03
    ª
    -1.94
    ³
    -1.93
    «
    -1.89
    ł
    -1.88
    ®
    -1.87
    POSITIVE LOGITS
    anova
    1.63
     nor
    1.63
     attenu
    1.63
    par
    1.55
     limiting
    1.49
    mp
    1.48
     stimulating
    1.48
     modulating
    1.45
     suppressing
    1.41
     regulating
    1.38
    Activations Density 0.144%

    No Known Activations