Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9084
    Prev
    Next
    INDEX
    Explanations

    terms related to different kinds of ownership or control, such as "consumer," "producers," "gun ownership," or "ivory trading."

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with consumption, ownership, and trade-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.80
    uci
    -0.70
    webkit
    -0.65
    £ı
    -0.61
    AUT
    -0.61
    é¾įå
    -0.61
    ascript
    -0.60
    OTUS
    -0.60
    Lv
    -0.59
    expression
    -0.59
    POSITIVE LOGITS
     statewide
    0.69
    itivity
    0.67
     worldwide
    0.65
    iasco
    0.65
    unta
    0.65
    ortium
    0.63
     nationwide
    0.63
     hotline
    0.63
    hops
    0.63
    stead
    0.60
    Activations Density 0.497%

    No Known Activations