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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 1078
    Prev
    Next
    INDEX
    Explanations

    mentions or references to Islamist groups or ideology

    oai_token-act-pair · gpt-3.5-turbo

    references to Islamist groups and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icles
    -0.83
    buck
    -0.78
    icle
    -0.76
     Myster
    -0.76
     Kear
    -0.73
    åħī
    -0.72
    Scot
    -0.72
     Drawn
    -0.72
     Dull
    -0.72
    thur
    -0.71
    POSITIVE LOGITS
     militant
    1.10
     extremist
    1.10
     extremists
    1.08
     Islamist
    1.05
     extremism
    1.03
     insurgent
    1.03
     jihadist
    1.01
     militants
    0.96
     radicals
    0.96
     insurgents
    0.94
    Activations Density 0.004%

    No Known Activations