© 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. 30613
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Cast."

    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
    285
    +0.14
    0.8%
    369
    +0.14
    0.8%
    211
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.14
    0.01
    263
    +0.14
    0.01
    122
    +0.13
    0.01
    Negative Logits
    ľ
    -5.48
    ĵ
    -5.37
    ł
    -5.11
    ı
    -4.96
    ĥ
    -4.95
    ¡
    -4.94
    ĥ½
    -4.93
    »¿
    -4.91
    »
    -4.82
    ħ
    -4.79
    POSITIVE LOGITS
    enstein
    2.02
    igan
    1.89
    away
    1.89
    liner
    1.88
    illon
    1.87
    iom
    1.83
    igation
    1.80
    erty
    1.78
    imen
    1.78
    bage
    1.77
    Activations Density 0.033%

    No Known Activations