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. 2-RES-JB
    6. 330
    Prev
    Next
    INDEX
    Explanations

    the word "route"

    oai_token-act-pair · gpt-4-turbo

    words related to travel routes and directions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific routes or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hem
    -0.86
    sle
    -0.85
    uster
    -0.83
     Hots
    -0.78
    minster
    -0.74
    oat
    -0.72
    mare
    -0.71
    aum
    -0.70
    orn
    -0.70
    luaj
    -0.70
    POSITIVE LOGITS
     routes
    1.28
     route
    1.26
    route
    1.19
    Route
    0.96
     Route
    0.91
     routing
    0.82
    nels
    0.81
    WAYS
    0.77
    WAY
    0.77
     Rout
    0.76
    Activations Density 0.010%

    No Known Activations