© 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. 29045
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "spoken."

    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
    144
    +0.16
    0.9%
    376
    +0.16
    0.9%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.16
    0.01
    462
    +0.16
    0.01
    351
    +0.11
    0.01
    Negative Logits
    ĥ½
    -3.54
    ĥ
    -3.23
    ¿½
    -3.22
    ¨
    -3.21
    ľ
    -3.15
     ↵
    -3.11
    ↵↵
    -3.11
     ↵
    -3.11
       ↵
    -3.11
    ↵
    -3.11
    POSITIVE LOGITS
    about
    1.60
    estry
    1.59
    dling
    1.57
     aloud
    1.57
    ienn
    1.54
    irl
    1.53
    ovo
    1.53
    oven
    1.52
    oslav
    1.48
    ahead
    1.48
    Activations Density 0.017%

    No Known Activations