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. 1-RES-JB
    6. 12750
    Prev
    Next
    INDEX
    Explanations

    references to exceptional intellectual ability or talent

    oai_token-act-pair · gpt-3.5-turbo

    references to genius, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Continued
    -0.89
    aver
    -0.88
    atern
    -0.73
    resp
    -0.69
    avan
    -0.68
    atana
    -0.68
    asca
    -0.66
    skirts
    -0.63
    akening
    -0.63
    than
    -0.63
    POSITIVE LOGITS
     genius
    1.27
    iuses
    0.97
    smanship
    0.94
     Genius
    0.87
     brilliance
    0.80
     talent
    0.77
    ocracy
    0.75
     mastermind
    0.75
     greatness
    0.74
    minded
    0.72
    Activations Density 0.012%

    No Known Activations