© 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. 26590
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jess" or "Jessica"

    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
    +0.17
    1.0%
    494
    +0.17
    0.9%
    369
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    292
    +0.17
    0.29
    310
    +0.17
    0.24
    160
    +0.15
    0.23
    Negative Logits
    TRODUCTION
    -1.70
     menos
    -1.60
    sis
    -1.59
    aneous
    -1.56
     ago
    -1.53
    aughter
    -1.53
    ancy
    -1.53
     tract
    -1.47
     anos
    -1.46
    phis
    -1.45
    POSITIVE LOGITS
    ilee
    1.67
    ![
    1.65
    ele
    1.57
    ie
    1.53
    up
    1.51
    angle
    1.51
    antine
    1.50
    tight
    1.47
    washed
    1.46
    amine
    1.42
    Activations Density 0.944%

    No Known Activations