© 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. 9-RES-JB
    11. 10410
    Prev
    Next
    INDEX
    Explanations

    the word "stroke" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "stroke" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bravo
    -0.68
    ainment
    -0.64
    ãĤ©
    -0.64
    atively
    -0.63
    ramid
    -0.62
    ãĥ¤
    -0.61
    resses
    -0.61
    arily
    -0.60
    iple
    -0.60
    ãĤ§
    -0.60
    POSITIVE LOGITS
    stem
    0.86
    kes
    0.80
    bil
    0.79
     stroke
    0.75
    pread
    0.74
    manship
    0.74
    flies
    0.68
    draw
    0.68
    teenth
    0.66
    jet
    0.66
    Activations Density 0.076%

    No Known Activations