© 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. 8-RES-JB
    11. 2052
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical abilities and skills, such as agility, strength, accuracy, and speed

    oai_token-act-pair · gpt-3.5-turbo

    qualities and attributes related to athletic performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Publication
    -0.80
    idays
    -0.78
     Federation
    -0.76
     commem
    -0.76
    endants
    -0.73
     Funding
    -0.72
    iatus
    -0.72
     Luxembourg
    -0.72
     Governments
    -0.72
     Discussion
    -0.71
    POSITIVE LOGITS
     athleticism
    1.51
     athlet
    1.43
     versatility
    1.42
     athletic
    1.29
     versatile
    1.19
     agility
    1.16
     toughness
    1.15
     explos
    1.14
     offensively
    1.13
     ability
    1.10
    Activations Density 0.604%

    No Known Activations