© 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. 30079
    Prev
    Next
    INDEX
    Explanations

    references to structured documents or data forms, particularly those labeled as "Sheet."

    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
    255
    +0.14
    0.9%
    376
    +0.13
    0.8%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    0.01
    181
    +0.13
    0.01
    273
    +0.12
    0.01
    Negative Logits
    "?"
    -2.02
     somebody
    -1.81
     spite
    -1.76
    '?"
    -1.75
     suppose
    -1.68
     say
    -1.65
     anybody
    -1.64
     yours
    -1.63
    '?
    -1.62
    't
    -1.59
    POSITIVE LOGITS
    ģ
    2.33
    ĻĤ
    2.29
    notes
    2.12
    Ł
    1.86
    Script
    1.81
    bank
    1.80
    £
    1.78
    ball
    1.78
    ¢
    1.74
    Ļ
    1.73
    Activations Density 0.009%

    No Known Activations