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. 6-RES-JB
    6. 22535
    Prev
    Next
    INDEX
    Explanations

    references to terrorist activities and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of terrorist activities or individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    galitarian
    -0.88
    laus
    -0.83
    shire
    -0.78
    )=(
    -0.76
    BuyableInstoreAndOnline
    -0.75
    ðĿ
    -0.74
    aver
    -0.74
    rose
    -0.69
    ais
    -0.69
    iband
    -0.69
    POSITIVE LOGITS
    abad
    1.05
     mastermind
    1.03
     bombings
    0.99
     terrorist
    0.95
     bombing
    0.95
     attacks
    0.94
     attack
    0.87
     terrorists
    0.87
     spree
    0.86
     retaliation
    0.86
    Activations Density 0.026%

    No Known Activations