© 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. 10-RES-JB
    11. 6558
    Prev
    Next
    INDEX
    Explanations

    words related to extremist groups and conflicts in the Middle East

    oai_token-act-pair · gpt-3.5-turbo

    references to various militant and terrorist organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Byron
    -0.84
     Hitch
    -0.77
     Edison
    -0.77
     Wally
    -0.75
     Lovecraft
    -0.74
     Wilde
    -0.73
     Hawth
    -0.73
     Shelley
    -0.73
     Cinderella
    -0.72
     Amelia
    -0.72
    POSITIVE LOGITS
    zbollah
    1.22
    akh
    1.19
    Syria
    1.14
    Syrian
    1.14
    ihadi
    1.14
    Nusra
    1.13
    addafi
    1.09
    usra
    1.09
    ISIS
    1.07
    Islam
    1.06
    Activations Density 0.213%

    No Known Activations