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. 19782
    Prev
    Next
    INDEX
    Explanations

    mentions of the terrorist group Al-Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to Al-Qaeda and its related activities

    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
     Seah
    -0.80
     Gron
    -0.80
     Constantin
    -0.76
     Vaugh
    -0.76
     Hubble
    -0.71
     Goodell
    -0.71
    ðĿ
    -0.70
    Beer
    -0.69
     Panasonic
    -0.69
    kj
    -0.69
    POSITIVE LOGITS
     affiliates
    1.04
     terrorists
    1.03
    istani
    0.97
     insurgents
    0.97
     insurgency
    0.95
     affiliate
    0.95
     fighters
    0.95
    aeda
    0.95
     operatives
    0.93
     bombings
    0.93
    Activations Density 0.028%

    No Known Activations