© 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 EvalsExportsinterp-engineNEWAPI 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. 30008
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "reveal."

    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
    376
    +0.19
    1.1%
    210
    +0.13
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.01
    59
    +0.13
    0.01
    218
    +0.12
    0.01
    Negative Logits
    izumab
    -1.65
     attention
    -1.52
    izer
    -1.43
     ${
    -1.40
    ancel
    -1.38
    ubot
    -1.38
    onto
    -1.33
    že
    -1.32
    app
    -1.31
    Topic
    -1.29
    POSITIVE LOGITS
    ilage
    1.91
    edly
    1.62
    iston
    1.55
    urized
    1.46
     Places
    1.39
    alter
    1.37
     oath
    1.36
     Leaf
    1.35
    eking
    1.35
    minster
    1.34
    Activations Density 0.015%

    No Known Activations