© 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. 8-RES-JB
    11. 3890
    Prev
    Next
    INDEX
    Explanations

    references related to the "Tour de France" race

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tour de France event

    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
    yip
    -0.69
    SourceFile
    -0.68
     corpus
    -0.68
    xon
    -0.65
    nikov
    -0.61
    ij士
    -0.60
    irlf
    -0.59
    angan
    -0.59
    icio
    -0.58
    ibrary
    -0.58
    POSITIVE LOGITS
     Duty
    0.97
    Merit
    0.73
    monary
    0.71
     duty
    0.70
    leave
    0.69
     Janeiro
    0.66
     Tours
    0.64
    Qual
    0.63
     Trance
    0.63
    opers
    0.63
    Activations Density 0.070%

    No Known Activations