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

    Neuronpedia

    Jacobian LensNEW
    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. 16609
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and references

    oai_token-act-pair · gpt-3.5-turbo

    references to sports-related content

    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
    wcs
    -0.82
     sidel
    -0.75
    zers
    -0.74
     miscar
    -0.70
    lessly
    -0.70
    ously
    -0.69
    ecause
    -0.67
    ufact
    -0.67
    oys
    -0.65
    vernment
    -0.65
    POSITIVE LOGITS
     Illustrated
    0.89
    Arizona
    0.84
     Analytics
    0.83
    Center
    0.81
     Inqu
    0.74
    manship
    0.74
    ESPN
    0.73
    Analysis
    0.72
    Business
    0.71
    avage
    0.70
    Activations Density 0.022%

    No Known Activations