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. 9-RES-JB
    6. 10558
    Prev
    Next
    INDEX
    Explanations

    terms related to cycling events like "Tour de France"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Tour de series, particularly with the word "de" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nyder
    -0.95
    yip
    -0.93
    xon
    -0.91
    blance
    -0.78
    tein
    -0.76
    nikov
    -0.75
    omsky
    -0.73
    quez
    -0.72
    ahime
    -0.71
    ement
    -0.70
    POSITIVE LOGITS
     Janeiro
    0.92
    Merit
    0.71
     Dangerous
    0.67
     Sciences
    0.64
     Discovery
    0.63
     Flags
    0.63
    DR
    0.62
     Trance
    0.62
     Endurance
    0.61
     Roses
    0.61
    Activations Density 0.053%

    No Known Activations