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. 1-RES-JB
    6. 17412
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist group "Al-Qaeda"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Al-Qaeda" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MAT
    -0.78
     Constantin
    -0.76
     Gron
    -0.75
     WM
    -0.74
    é¾įå
    -0.72
     Finnish
    -0.68
     Scher
    -0.68
     KR
    -0.68
    Ö¼
    -0.68
     Hardy
    -0.68
    POSITIVE LOGITS
    Qaeda
    1.11
    Qaida
    1.06
    istani
    0.91
    aeda
    0.91
     mosqu
    0.91
    gebra
    0.88
     hijacked
    0.87
     Qaeda
    0.86
     bombings
    0.83
    querque
    0.83
    Activations Density 0.010%

    No Known Activations