© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 22215
    Prev
    Next
    INDEX
    Explanations

    keywords related to incitement or provocation

    oai_token-act-pair · gpt-3.5-turbo

    words related to incitement and provocation of violence or unrest

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

    No Comments

    Negative Logits
     ellipt
    -0.79
    rieve
    -0.70
    neau
    -0.69
    rost
    -0.66
    otiation
    -0.65
    aird
    -0.63
     Garrison
    -0.63
    usterity
    -0.61
     Eucl
    -0.61
    erm
    -0.61
    POSITIVE LOGITS
     inciting
    1.01
     sidx
    1.01
    itement
    0.93
    xual
    0.88
     incite
    0.87
    ãĥĥ
    0.86
    ãĥ¼ãĥĨãĤ£
    0.81
    ãĥŁ
    0.78
    TextColor
    0.78
     stoked
    0.77
    Activations Density 0.036%

    No Known Activations