© 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. 28688
    Prev
    Next
    INDEX
    Explanations

    references to the act of eating or food consumption

    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
    +0.22
    1.3%
    376
    +0.17
    1.0%
    407
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.22
    0.03
    218
    +0.17
    0.03
    138
    +0.17
    0.02
    Negative Logits
    Ŀ
    -2.40
    ı
    -2.40
    Ń
    -2.19
    ĥ½
    -2.19
    ĭ
    -2.18
    ŀ
    -2.12
    §
    -2.08
    Ĥ
    -2.06
    Ł
    -2.04
    ķ
    -2.03
    POSITIVE LOGITS
    fors
    1.78
    caster
    1.67
    etic
    1.61
    etz
    1.52
    etics
    1.50
    able
    1.50
    ative
    1.50
     Gh
    1.47
     deprived
    1.46
    spoken
    1.46
    Activations Density 0.092%

    No Known Activations