© 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. 6-RES-JB
    11. 5580
    Prev
    Next
    INDEX
    Explanations

    mentions of specific highways and roadways

    oai_token-act-pair · gpt-3.5-turbo

    references to interstate roadways and travel-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.98
    */(
    -0.89
    avers
    -0.86
    room
    -0.86
    ebook
    -0.84
    isters
    -0.77
     Nanto
    -0.75
    eful
    -0.75
    =-=-=-=-=-=-=-=-
    -0.73
    arters
    -0.73
    POSITIVE LOGITS
     Highway
    0.97
     highway
    0.97
     highways
    0.96
     Interstate
    0.91
     Speedway
    0.82
     Powers
    0.81
     Route
    0.80
     Traffic
    0.80
     freeway
    0.79
     Railroad
    0.77
    Activations Density 0.035%

    No Known Activations