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. 7-RES-JB
    6. 6659
    Prev
    Next
    INDEX
    Explanations

    mentions of the extremist group "Boko Haram"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the group Boko Haram and related entities or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    miss
    -0.69
    Frameworks
    -0.68
    hold
    -0.64
    y
    -0.64
    croft
    -0.63
    lect
    -0.63
    myra
    -0.63
    grave
    -0.62
    cream
    -0.62
    galitarian
    -0.60
    POSITIVE LOGITS
    atta
    0.75
    oulos
    0.75
    illin
    0.73
    uba
    0.73
    tml
    0.71
    elta
    0.70
    hammad
    0.69
    ulhu
    0.69
    iazep
    0.67
    ipal
    0.67
    Activations Density 0.184%

    No Known Activations