© 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. 8330
    Prev
    Next
    INDEX
    Explanations

    names containing the syllable "leg"

    oai_token-act-pair · gpt-3.5-turbo

    references to sports, particularly related to athletic leagues and competitions

    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
     setting
    -0.59
     ticking
    -0.58
     dividing
    -0.55
     stars
    -0.54
     departure
    -0.54
     Walters
    -0.53
     Tate
    -0.53
     tariffs
    -0.52
     Bake
    -0.52
    stars
    -0.52
    POSITIVE LOGITS
    itimate
    1.10
    rant
    0.99
    rett
    0.99
    edly
    0.95
    heny
    0.92
    ibility
    0.90
    RIP
    0.87
    lav
    0.86
    isl
    0.86
    rity
    0.85
    Activations Density 0.018%

    No Known Activations