Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16088
    Prev
    Next
    INDEX
    Explanations

    references to the cycling event "Tour de France"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the phrase "Tour de" followed by various references or events related to cycling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    untled
    -0.76
    htaking
    -0.70
    omsky
    -0.68
    ovie
    -0.68
    blance
    -0.67
    rils
    -0.67
    ement
    -0.66
    onson
    -0.65
    nyder
    -0.65
    alyst
    -0.65
    POSITIVE LOGITS
     Janeiro
    1.30
     los
    0.96
    lla
    0.91
     Mayo
    0.88
    utsche
    0.81
     France
    0.81
     la
    0.80
    utsch
    0.79
     Portugal
    0.77
     Chile
    0.77
    Activations Density 0.027%

    No Known Activations