© 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. 29442
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Wright."

    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
    410
    +0.14
    0.8%
    369
    +0.14
    0.8%
    22
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.14
    0.01
    22
    +0.14
    0.01
    34
    +0.13
    0.01
    Negative Logits
    ity
    -1.65
    anc
    -1.48
    aying
    -1.48
     suppose
    -1.47
     mean
    -1.43
     accused
    -1.43
     entirety
    -1.43
     discl
    -1.43
     older
    -1.41
     deletion
    -1.39
    POSITIVE LOGITS
    pson
    2.04
    genstein
    1.99
    ģ
    1.96
    Ģ
    1.95
    º
    1.93
    yard
    1.89
    yards
    1.86
    ª
    1.82
    į
    1.82
    »
    1.82
    Activations Density 0.077%

    No Known Activations