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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17723
    Prev
    Next
    INDEX
    Explanations

    mentions of specific cycling races, particularly the Tour de France

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tour de France

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proport
    -0.72
    rew
    -0.71
    arial
    -0.69
    ooked
    -0.65
    bread
    -0.64
    icago
    -0.63
     sustaining
    -0.63
    milo
    -0.63
    initions
    -0.62
    isSpecialOrderable
    -0.61
    POSITIVE LOGITS
     Tour
    1.22
    neys
    1.08
     Tours
    1.03
    Tour
    1.00
    neau
    0.88
    ney
    0.87
     tour
    0.84
     itiner
    0.80
    athon
    0.78
    engers
    0.76
    Activations Density 0.006%

    No Known Activations