© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1231
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating completion or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate deadlines or endpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uni
    -0.72
    itsch
    -0.63
    avorite
    -0.63
     ub
    -0.61
    Interested
    -0.61
    hemy
    -0.61
     Parenthood
    -0.61
    ufact
    -0.60
    dinand
    -0.60
    agine
    -0.58
    POSITIVE LOGITS
    owment
    1.42
    ocrine
    1.08
    angering
    1.06
    game
    0.97
    points
    0.88
    ocrin
    0.84
     thereof
    0.82
    urance
    0.81
    liest
    0.80
    notes
    0.80
    Activations Density 0.034%

    No Known Activations