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. 8-RES-JB
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    mentions or references to extremist groups and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to extremist groups and ideologies

    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
    aird
    -0.81
    fman
    -0.80
    arest
    -0.78
    sburgh
    -0.72
    nect
    -0.70
    ilet
    -0.70
    ËĪ
    -0.68
    FACE
    -0.68
    umm
    -0.67
     Minotaur
    -0.67
    POSITIVE LOGITS
     extremists
    1.05
     extremist
    1.03
     extremism
    1.01
     Islamist
    0.99
     ideologies
    0.95
     Islamists
    0.94
     fringe
    0.91
     ideology
    0.90
     groups
    0.89
     jihadists
    0.87
    Activations Density 0.048%

    No Known Activations