© 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. 21419
    Prev
    Next
    INDEX
    Explanations

    mentions of transportation related terms and locations

    oai_token-act-pair · gpt-3.5-turbo

    significant events or occurrences related to transportation issues or emergencies

    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
    natureconservancy
    -0.84
     bee
    -0.83
     cigars
    -0.81
     Bees
    -0.79
     Cookies
    -0.77
     Palm
    -0.77
    icum
    -0.76
     paternity
    -0.76
    wcsstore
    -0.75
     Pagan
    -0.74
    POSITIVE LOGITS
     trains
    2.04
     Amtrak
    1.90
     rail
    1.82
     railways
    1.77
    Rail
    1.77
     Rail
    1.75
     train
    1.74
     subway
    1.72
     commuter
    1.71
     locom
    1.69
    Activations Density 0.511%

    No Known Activations