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. 10-RES-JB
    6. 19644
    Prev
    Next
    INDEX
    Explanations

    references to the NCAA (National Collegiate Athletic Association)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to NCAA and FIFA

    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
    ander
    -0.73
    othal
    -0.72
    achus
    -0.71
     Hera
    -0.70
    mith
    -0.67
    itars
    -0.66
    acly
    -0.66
    >>>>
    -0.65
    alez
    -0.65
    ppel
    -0.65
    POSITIVE LOGITS
     Tournament
    1.02
     sanctioned
    0.85
     sanctions
    0.81
     Playoffs
    0.81
     Regulations
    0.80
     Basketball
    0.80
     Football
    0.79
    PDATE
    0.79
     tournament
    0.79
     Division
    0.79
    Activations Density 0.026%

    No Known Activations