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

    Neuronpedia

    APICircuit 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. 19393
    Prev
    Next
    INDEX
    Explanations

    mentions of activities related to biking

    oai_token-act-pair · gpt-3.5-turbo

    topics related to biking and its associated risks or experiences

    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
     Saddam
    -0.91
    agents
    -0.86
     Starg
    -0.86
    Iraq
    -0.81
    Howard
    -0.79
     Prescott
    -0.78
     Gingrich
    -0.77
    egu
    -0.77
     Manafort
    -0.76
     Freud
    -0.76
    POSITIVE LOGITS
     bikes
    2.49
     bike
    2.48
     Bike
    2.34
     cyclists
    2.32
     biking
    2.27
     bicycles
    2.20
     bicycle
    2.19
     cycling
    2.18
     cyclist
    2.17
     Cycling
    2.16
    Activations Density 0.448%

    No Known Activations