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. 7-RES-JB
    6. 10144
    Prev
    Next
    INDEX
    Explanations

    phrases related to a male individual, often related to politics or leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "He" in a political context

    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
    aimon
    -0.69
     Columb
    -0.67
    earch
    -0.64
    cgi
    -0.63
    ective
    -0.62
     Village
    -0.62
     Dane
    -0.62
     Leigh
    -0.61
    hooting
    -0.61
     Leban
    -0.61
    POSITIVE LOGITS
    zbollah
    1.39
    eded
    1.10
    'll
    1.09
    'd
    1.06
     campaigned
    0.99
    resy
    0.98
     appoint
    0.92
    've
    0.92
     tweeted
    0.91
     vetoed
    0.89
    Activations Density 0.226%

    No Known Activations