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. 11-RES-JB
    6. 15397
    Prev
    Next
    INDEX
    Explanations

    specific references to a provincial park called "Algonquin Provincial Park"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific parks or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.97
    Ò
    -0.92
     Typh
    -0.92
    ichick
    -0.89
    emic
    -0.88
    Lua
    -0.87
    Ñĥ
    -0.86
    luaj
    -0.85
    ierre
    -0.82
    Tai
    -0.82
    POSITIVE LOGITS
     park
    2.47
    Park
    2.29
     parks
    2.24
     Park
    2.23
    park
    2.15
     Parks
    2.02
     PARK
    1.79
     Parker
    1.50
     Parking
    1.45
     ranger
    1.44
    Activations Density 0.340%

    No Known Activations