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. 459
    Prev
    Next
    INDEX
    Explanations

    mentions of international law terms related to Sharia courts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sharia" and related contexts

    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
    REDACTED
    -0.71
    asus
    -0.70
    anwhile
    -0.69
    é¾įå¥ij士
    -0.66
    WP
    -0.65
     Seller
    -0.65
    hiro
    -0.64
    NetMessage
    -0.64
    milo
    -0.63
    ATS
    -0.63
    POSITIVE LOGITS
    pton
    1.21
    ples
    1.18
    pling
    1.09
    ãĥ£
    1.08
    pless
    1.01
    ply
    1.00
    ning
    1.00
    riors
    1.00
    pering
    0.97
    pen
    0.93
    Activations Density 0.020%

    No Known Activations