© 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. 10-RES-JB
    11. 16106
    Prev
    Next
    INDEX
    Explanations

    basketball-related terms and skills

    oai_token-act-pair · gpt-3.5-turbo

    athletic abilities and performance metrics in sports

    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
     Seat
    -0.87
     ABE
    -0.77
     Principal
    -0.68
     ashes
    -0.67
     laureate
    -0.67
    netflix
    -0.66
     ANN
    -0.66
     Banner
    -0.65
     Sponsor
    -0.65
     Waste
    -0.65
    POSITIVE LOGITS
     skills
    1.16
     technique
    1.09
     tendencies
    1.09
     offensively
    1.07
     drills
    1.04
     athleticism
    1.04
     ability
    1.03
     prowess
    1.03
     instincts
    1.01
     repertoire
    1.00
    Activations Density 0.244%

    No Known Activations