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. 11-RES-JB
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    references to positions of authority or importance such as "high court" or "president."

    oai_token-act-pair · gpt-3.5-turbo

    references to high-ranking individuals or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
    undo
    -0.74
    vous
    -0.69
    unia
    -0.63
     Wonderland
    -0.61
    heim
    -0.61
    в
    -0.60
     Mania
    -0.60
    Dear
    -0.58
     Slug
    -0.58
    POSITIVE LOGITS
    ranking
    1.01
    profile
    0.97
     profile
    0.97
    handed
    0.93
    landers
    0.89
     ranking
    0.89
    court
    0.87
     bidder
    0.85
    powered
    0.83
     court
    0.83
    Activations Density 0.061%

    No Known Activations