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. 16611
    Prev
    Next
    INDEX
    Explanations

    references to lanes, especially in the context of transportation infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "lanes," particularly in the context of traffic or transportation

    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
    Attempts
    -0.69
     Extrem
    -0.68
    ISE
    -0.67
     Fighters
    -0.67
    anamo
    -0.67
     Aerospace
    -0.65
    OLOG
    -0.65
     FOX
    -0.65
     EDITION
    -0.64
    UM
    -0.64
    POSITIVE LOGITS
     lanes
    1.42
    lane
    1.25
     lane
    1.16
    wagon
    0.90
     highways
    0.84
    chwitz
    0.84
     ramps
    0.82
    wagen
    0.81
    pread
    0.81
    pace
    0.81
    Activations Density 0.003%

    No Known Activations