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. 0-RES-JB
    6. 24140
    Prev
    Next
    INDEX
    Explanations

    mentions of the terrorist group "Al-Qaeda"

    oai_token-act-pair · gpt-3.5-turbo

    references to al-Qaeda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pass
    -0.75
     pl
    -0.70
     offic
    -0.67
     wall
    -0.67
     stare
    -0.67
     decor
    -0.66
     exterior
    -0.64
     barrier
    -0.64
     review
    -0.64
     glare
    -0.63
    POSITIVE LOGITS
    Qaeda
    3.53
    Qaida
    2.95
    Nusra
    2.09
     Qaeda
    1.45
     Laden
    1.25
    CIA
    1.23
    Assad
    1.15
    ihadi
    1.14
    terrorist
    1.12
    zbollah
    1.10
    Activations Density 0.009%

    No Known Activations