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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14433
    Prev
    Next
    INDEX
    Explanations

    descriptions related to vehicles such as trucks, SUVs, boats, and bicycles

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and transportation systems

    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
     Diss
    -0.84
     Rosenberg
    -0.73
     Codex
    -0.72
     Promise
    -0.72
     Corruption
    -0.72
     Outbreak
    -0.72
     Frag
    -0.70
     Unicode
    -0.69
    philis
    -0.69
     Bleach
    -0.68
    POSITIVE LOGITS
     motorcycles
    1.59
     taxis
    1.52
     bicycles
    1.50
     trucks
    1.45
     vans
    1.44
     bikes
    1.42
     tractor
    1.42
     vehicles
    1.42
     locom
    1.35
     towed
    1.34
    Activations Density 0.388%

    No Known Activations