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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7685
    Prev
    Next
    INDEX
    Explanations

    references to roads and driving-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to roads and road-related terminology

    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
    arians
    -0.78
    tle
    -0.75
    volent
    -0.71
    uating
    -0.65
     Eps
    -0.63
     Wynne
    -0.62
     Mons
    -0.62
    ascript
    -0.62
    uates
    -0.62
     ears
    -0.61
    POSITIVE LOGITS
    blocks
    1.37
    trip
    1.27
    block
    1.26
    show
    1.23
    ways
    1.16
    side
    1.11
    map
    1.11
    kill
    1.06
    runner
    1.06
    maps
    1.05
    Activations Density 0.037%

    No Known Activations