Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14905
    Prev
    Next
    INDEX
    Explanations

    locations or references related to highways, specifically Highway 9

    oai_token-act-pair · gpt-3.5-turbo

    references to specific highways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.84
    eries
    -0.79
    ever
    -0.78
    tle
    -0.76
    avers
    -0.74
    encer
    -0.73
    ecast
    -0.72
    rooms
    -0.71
    ertain
    -0.70
    eller
    -0.70
    POSITIVE LOGITS
     Highway
    1.23
     Route
    0.95
     Roads
    0.88
     highways
    0.88
     roads
    0.84
     checkpoints
    0.84
     Simulator
    0.83
     highway
    0.80
     artery
    0.80
     Parkway
    0.79
    Activations Density 0.005%

    No Known Activations