© 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. 28819
    Prev
    Next
    INDEX
    Explanations

    references to peanuts or peanut products

    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
    457
    +0.15
    0.9%
    317
    +0.14
    0.8%
    306
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.15
    0.01
    48
    +0.14
    0.01
    451
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.87
    ¿½
    -2.38
    Ń
    -2.37
    Ĥ
    -2.11
    ĭ
    -2.07
    Īĺ
    -2.02
    ĺ
    -1.86
    Ĭ
    -1.85
    Ĺ
    -1.82
    ĸ´
    -1.78
    POSITIVE LOGITS
    rett
    1.80
    ek
    1.79
    FC
    1.66
    ÅĽci
    1.63
    leen
    1.61
    rette
    1.55
    ppo
    1.53
    zilla
    1.50
    ÅĽ
    1.50
    bellum
    1.49
    Activations Density 0.050%

    No Known Activations