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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17370
    Prev
    Next
    INDEX
    Explanations

    words related to outdoor activities and sports such as ice, long-track speed skating, cycling, and hunting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various sports and recreational activities

    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
     Malf
    -0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     Rosenberg
    -0.65
     spoiled
    -0.65
     Pompe
    -0.65
     fingerprints
    -0.63
     Rasmussen
    -0.63
     Benef
    -0.62
     culprit
    -0.62
     Luxem
    -0.62
    POSITIVE LOGITS
    iculture
    1.05
    boarding
    1.05
    athlon
    1.02
    gaming
    1.02
    otherapy
    1.01
    boxing
    0.99
    restling
    0.96
    sports
    0.94
    hooting
    0.93
    anship
    0.91
    Activations Density 0.417%

    No Known Activations