Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 249
    Prev
    Next
    INDEX
    Explanations

    terminology related to the NBA (National Basketball Association) and basketball in general

    oai_token-act-pair · gpt-3.5-turbo

    mentions of professional basketball leagues, primarily the NBA

    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
    nir
    -0.80
    adow
    -0.80
    anamo
    -0.80
    essage
    -0.78
    terday
    -0.77
    combe
    -0.76
     McAuliffe
    -0.76
    utils
    -0.75
    bery
    -0.69
    atche
    -0.69
    POSITIVE LOGITS
     Playoffs
    1.07
     Players
    1.02
    PA
    0.99
     Draft
    0.93
     Playoff
    0.92
     Finals
    0.89
     Championship
    0.88
     Commissioner
    0.87
     Rookie
    0.86
     lockout
    0.86
    Activations Density 0.045%

    No Known Activations