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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4129
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist organization Al-Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    the term "al-Qaeda" or related references to the organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twain
    -0.80
    mble
    -0.66
     Pixar
    -0.65
    ALLY
    -0.64
    EEE
    -0.63
    gerald
    -0.63
     Lovecraft
    -0.63
     Vaugh
    -0.63
     grate
    -0.62
     wip
    -0.62
    POSITIVE LOGITS
     Qaeda
    1.43
    Qaeda
    1.32
     Jazeera
    1.25
    Qaida
    1.18
    Assad
    1.07
     Baghd
    1.03
     Sharia
    1.02
    aida
    1.01
     Assad
    0.98
    Nusra
    0.97
    Activations Density 0.025%

    No Known Activations