© 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. 28689
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "key."

    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
    148
    +0.14
    0.8%
    376
    +0.13
    0.7%
    201
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.14
    0.04
    57
    +0.13
    0.03
    44
    +0.11
    0.03
    Negative Logits
    ounder
    -1.47
    itness
    -1.46
    keit
    -1.44
    chio
    -1.42
     present
    -1.41
    ribut
    -1.38
    ocus
    -1.38
    ³
    -1.36
    mber
    -1.35
    chie
    -1.33
    POSITIVE LOGITS
    hole
    2.30
    holes
    2.01
    buk
    2.00
    stroke
    1.86
    bind
    1.84
    stro
    1.80
    quarters
    1.73
    emas
    1.66
    faces
    1.65
    poses
    1.58
    Activations Density 5.265%

    No Known Activations