Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7908
    Prev
    Next
    INDEX
    Explanations

    mentions of extremism or radical ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to radicalism and extremist ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.82
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    ĸļ
    -0.68
    FACE
    -0.64
    aird
    -0.64
    rost
    -0.62
    veyard
    -0.62
    ords
    -0.62
    ust
    -0.60
    luster
    -0.60
    POSITIVE LOGITS
     Islamists
    1.28
    ization
    1.25
     Islamist
    1.22
    isation
    1.19
    ized
    1.17
     Islam
    1.12
    izing
    1.11
     Islamic
    1.06
    ism
    1.05
    izers
    1.04
    Activations Density 0.053%

    No Known Activations