© 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. 25725
    Prev
    Next
    INDEX
    Explanations

    the word "most" signifying superlative descriptions or prioritization

    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
    170
    +0.14
    0.8%
    239
    +0.12
    0.7%
    237
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.14
    0.09
    237
    +0.12
    0.08
    239
    +0.11
    0.07
    Negative Logits
    ±
    -2.29
    º
    -2.00
    ·
    -1.88
    Ł
    -1.86
    ¹
    -1.86
     accordingly
    -1.82
    ´
    -1.81
    ¢
    -1.73
    Ĭ
    -1.69
    §
    -1.67
    POSITIVE LOGITS
     novels
    1.50
     collaborators
    1.49
     collaboration
    1.47
     conceivable
    1.41
    izza
    1.40
    ighters
    1.40
     Americans
    1.39
    quilibrium
    1.39
    igator
    1.38
     Collaboration
    1.37
    Activations Density 1.719%

    No Known Activations