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. 0-RES-JB
    6. 17202
    Prev
    Next
    INDEX
    Explanations

    the name "Bryant"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bryant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rans
    -0.76
     Sakuya
    -0.70
     sv
    -0.68
    Ï
    -0.67
     english
    -0.66
     vessel
    -0.66
     alt
    -0.64
     Pirate
    -0.64
    waves
    -0.63
     CT
    -0.62
    POSITIVE LOGITS
     Bryant
    3.99
     Kobe
    1.62
     Lakers
    1.33
     Baldwin
    1.31
     Pryor
    1.28
     Lowry
    1.27
     Staples
    1.21
     Romo
    1.19
     Ingram
    1.17
     Chandler
    1.17
    Activations Density 0.021%

    No Known Activations