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. 7-RES-JB
    6. 16219
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords related to the United Kingdom

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "UK"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rods
    -0.78
    cler
    -0.71
     Shots
    -0.69
     breaths
    -0.68
    BOOK
    -0.67
    owder
    -0.67
    addock
    -0.67
    iquid
    -0.67
     packets
    -0.66
     shots
    -0.65
    POSITIVE LOGITS
    istani
    0.86
     Isles
    0.80
     Embassy
    0.79
     Airways
    0.77
    mare
    0.76
     Columb
    0.75
     Parliament
    0.73
     Antarctic
    0.71
     Columbia
    0.70
    orea
    0.69
    Activations Density 0.040%

    No Known Activations