© 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. 29907
    Prev
    Next
    INDEX
    Explanations

    occurrences of the closing bracket character

    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
    362
    +0.12
    0.7%
    85
    +0.12
    0.6%
    20
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.12
    0.06
    258
    +0.12
    0.06
    155
    +0.11
    0.05
    Negative Logits
    ª
    -2.64
    Īĺ
    -2.56
    ľĵ
    -2.46
    ķ
    -2.37
    ¤
    -2.31
    ¿
    -2.07
    ĸ
    -2.03
    Ĵ
    -1.99
    ¬
    -1.99
    º
    -1.94
    POSITIVE LOGITS
    icity
    1.59
     measure
    1.57
    ality
    1.48
     industry
    1.48
    ium
    1.47
    ariat
    1.46
     benefit
    1.45
    chers
    1.44
    inger
    1.42
    als
    1.41
    Activations Density 0.056%

    No Known Activations