© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 7207
    Prev
    Next
    INDEX
    Explanations

    references to basketball

    oai_token-act-pair · gpt-3.5-turbo

    mentions of basketball

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Sports-related features
    volleyball is also here

    No Comments

    Negative Logits
    ktop
    -0.79
     Ples
    -0.75
    ablishment
    -0.74
    UTC
    -0.73
    utter
    -0.67
    akin
    -0.64
    Border
    -0.64
    rans
    -0.64
     Dispatch
    -0.64
    imate
    -0.61
    POSITIVE LOGITS
     basketball
    0.90
     volleyball
    0.78
    basketball
    0.77
     scholarships
    0.73
     balls
    0.73
    sticks
    0.73
     hockey
    0.73
    birds
    0.72
    asketball
    0.72
     Basketball
    0.72
    Activations Density 0.036%

    No Known Activations