© 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. 28797
    Prev
    Next
    INDEX
    Explanations

    references to "prop" as it's a common term in programming and component definitions

    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
    429
    +0.12
    0.7%
    300
    +0.11
    0.7%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.02
    177
    +0.11
    0.01
    385
    +0.11
    0.01
    Negative Logits
    Ĺ
    -2.91
    Ń
    -2.77
    ĸ´
    -2.50
    Ĭ
    -2.48
    ľ
    -2.43
    Ĥ
    -2.39
    ·¸
    -2.36
    °
    -2.34
    ´
    -2.32
    µ
    -2.27
    POSITIVE LOGITS
    abad
    1.78
    idium
    1.77
    abase
    1.76
    aceous
    1.73
    ’
    1.70
    maker
    1.65
    ibase
    1.63
    inqu
    1.63
    zilla
    1.62
    ech
    1.62
    Activations Density 0.022%

    No Known Activations