© 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. 2-MLP-SM
    11. 24937
    Prev
    Next
    INDEX
    Explanations

    references to art and artistic concepts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    403
    +0.14
    0.8%
    431
    +0.13
    0.7%
    411
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.14
    0.02
    459
    +0.13
    0.02
    404
    +0.12
    0.02
    Negative Logits
    ª
    -3.33
    «
    -3.15
    Ħ
    -2.83
    ¥
    -2.78
    Ģ
    -2.77
    ģ
    -2.74
    ĵ
    -2.71
    Ĩ
    -2.69
    ħ
    -2.69
    ĥ
    -2.66
    POSITIVE LOGITS
    ento
    1.62
    '">
    1.49
    ...'
    1.47
    zos
    1.46
    zo
    1.45
    áĢ¬
    1.43
    ãģ¾ãģĽãĤĵ
    1.43
    áĢ¯
    1.42
    :'
    1.42
    '):
    1.41
    Activations Density 0.090%

    No Known Activations