© 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. 0-RES-JB
    11. 426
    Prev
    Next
    INDEX
    Explanations

    transportation-related terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to transportation-related entities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     witch
    -0.74
     clone
    -0.68
     princess
    -0.66
     rook
    -0.65
     crystal
    -0.65
     stal
    -0.63
     holy
    -0.63
     crystals
    -0.63
     nin
    -0.63
     abs
    -0.62
    POSITIVE LOGITS
     Transportation
    3.67
     Transport
    1.98
     Transit
    1.75
     Aviation
    1.49
     TSA
    1.48
     transportation
    1.46
     Traffic
    1.41
     Telecommunications
    1.38
     Tourism
    1.32
     DOT
    1.31
    Activations Density 0.019%

    No Known Activations