© 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. 30359
    Prev
    Next
    INDEX
    Explanations

    instances of the word "component" in the text

    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
    245
    +0.10
    0.6%
    452
    +0.10
    0.6%
    117
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.10
    0.01
    117
    +0.10
    0.01
    448
    +0.10
    0.01
    Negative Logits
    Ĥ¬
    -3.63
    ³
    -3.07
    ĨĴ
    -3.06
    ·
    -3.00
    ĥ½
    -2.98
    Ń
    -2.94
    ľ
    -2.93
    ĻĤ
    -2.83
    ²
    -2.80
    ´
    -2.79
    POSITIVE LOGITS
    cias
    1.81
    ball
    1.77
    edly
    1.72
    etes
    1.71
    bol
    1.66
    folio
    1.66
    ellar
    1.65
    plates
    1.63
    igue
    1.62
    nell
    1.60
    Activations Density 0.043%

    No Known Activations