© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27877
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ra."

    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
    +0.15
    0.9%
    73
    +0.13
    0.8%
    246
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.15
    0.01
    73
    +0.13
    0.01
    415
    +0.13
    0.01
    Negative Logits
    ¿½
    -2.75
    ı
    -2.55
    ĥ½
    -2.47
    ĩ
    -2.46
    ij
    -2.44
    İ
    -2.23
    ĵ
    -2.19
    ª
    -2.13
    Īĺ
    -2.11
    ĭ
    -2.03
    POSITIVE LOGITS
    handling
    1.64
    icum
    1.56
    supported
    1.55
    ids
    1.52
    ú
    1.52
    uid
    1.49
    plist
    1.48
    iders
    1.48
    udi
    1.47
    ist
    1.43
    Activations Density 0.006%

    No Known Activations