© 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. 30497
    Prev
    Next
    INDEX
    Explanations

    references to the name "Gibson."

    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
    +0.16
    0.9%
    230
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.16
    0.01
    43
    +0.14
    0.01
    410
    +0.14
    0.01
    Negative Logits
     her
    -1.72
    fection
    -1.70
     greeting
    -1.65
     deaf
    -1.59
     shortening
    -1.57
    ters
    -1.55
     toward
    -1.54
    tering
    -1.49
    board
    -1.45
     hers
    -1.45
    POSITIVE LOGITS
    ģ
    2.74
    Īĺ
    2.71
    »
    2.55
    ĻĤ
    2.54
    Ľ
    2.44
    ª
    2.43
    Ģ
    2.36
    ²
    2.31
    Ĵ
    2.31
    ½
    2.28
    Activations Density 0.014%

    No Known Activations