© 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. 11-RES-JB
    11. 21251
    Prev
    Next
    INDEX
    Explanations

    years and specific events related to motorsports

    oai_token-act-pair · gpt-3.5-turbo

    references to specific racing events or motorsport-related statistics

    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
     Bungie
    -0.83
    gat
    -0.73
    Netflix
    -0.72
     Chomsky
    -0.71
    tsy
    -0.71
    anamo
    -0.70
    isine
    -0.68
    ItemTracker
    -0.68
     Barnes
    -0.68
    netflix
    -0.67
    POSITIVE LOGITS
     Daytona
    1.24
     races
    1.21
     FIA
    1.21
     championships
    1.19
     Motorsport
    1.19
     Rally
    1.15
     Endurance
    1.11
     Races
    1.11
     race
    1.09
     racing
    1.09
    Activations Density 0.201%

    No Known Activations