© 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. 10707
    Prev
    Next
    INDEX
    Explanations

    references to the "Tour de France" cycling event

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tour de France and related events

    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
    xon
    -0.68
    yip
    -0.65
     narration
    -0.61
    ascript
    -0.60
    rison
    -0.59
    netflix
    -0.59
    dylib
    -0.58
    steen
    -0.57
    blance
    -0.57
    udic
    -0.57
    POSITIVE LOGITS
     Duty
    0.82
    Merit
    0.70
     Tours
    0.69
     Ride
    0.68
     Guang
    0.67
     Champions
    0.64
    ennes
    0.64
     Luxembourg
    0.63
     France
    0.63
     Europe
    0.62
    Activations Density 0.042%

    No Known Activations