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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3622
    Prev
    Next
    INDEX
    Explanations

    words related to roads, highways, and transportation infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to interstate highways and related geographical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.90
     Nanto
    -0.89
    */(
    -0.84
    isters
    -0.80
    room
    -0.78
    ebook
    -0.78
    fman
    -0.77
    avers
    -0.75
    chers
    -0.72
    arters
    -0.71
    POSITIVE LOGITS
     highways
    1.08
     Highway
    1.05
     highway
    1.02
     Interstate
    0.98
     Parkway
    0.88
     Commerce
    0.84
     Route
    0.83
     Traffic
    0.83
     Railroad
    0.82
     freeway
    0.81
    Activations Density 0.019%

    No Known Activations