© 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. 28388
    Prev
    Next
    INDEX
    Explanations

    references to the pancreas and related health conditions

    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
    +0.17
    1.0%
    94
    +0.10
    0.6%
    93
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.17
    0.01
    453
    +0.10
    0.01
    94
    +0.10
    0.01
    Negative Logits
    ı
    -2.83
    ¯
    -2.78
    §
    -2.66
    «
    -2.57
    ĭ
    -2.51
    ¶
    -2.49
    Ķ
    -2.48
    Ĥ
    -2.44
    ĺ
    -2.41
    İ
    -2.39
    POSITIVE LOGITS
    entially
    1.83
    sheet
    1.73
    arium
    1.70
    illar
    1.63
    icolor
    1.62
    pere
    1.60
    istine
    1.58
    imeter
    1.56
     burner
    1.54
    ential
    1.52
    Activations Density 0.006%

    No Known Activations