© 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. 30720
    Prev
    Next
    INDEX
    Explanations

    references to the Chrome web browser or its components

    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
    129
    +0.14
    0.8%
    317
    +0.13
    0.8%
    19
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.14
    0.01
    317
    +0.13
    0.01
    129
    +0.13
    0.01
    Negative Logits
    Ĥ
    -3.21
    ĺ
    -3.20
    Ĺ
    -3.09
    ĭ
    -2.97
    Ĭ
    -2.86
    Ĥ¬
    -2.82
    Ħ
    -2.81
    ¦
    -2.78
    ı
    -2.75
    ij
    -2.66
    POSITIVE LOGITS
    "}](#
    2.00
    krit
    1.88
    aurus
    1.82
    edly
    1.82
    hurst
    1.79
    gary
    1.76
    chaft
    1.70
     vols
    1.69
    helf
    1.67
    bourne
    1.64
    Activations Density 0.033%

    No Known Activations