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. 3-RES-JB
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "British Columbia."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of British Columbia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĻ
    -0.83
    ãĤ¯
    -0.81
    inka
    -0.78
    ãĤ·ãĥ£
    -0.77
    Oracle
    -0.74
     Rove
    -0.67
    ischer
    -0.66
    bug
    -0.65
    ãĥŀ
    -0.65
     Kare
    -0.65
    POSITIVE LOGITS
    upid
    1.00
     Heights
    0.96
     Territories
    0.90
     Territory
    0.84
     Residents
    0.80
    istan
    0.79
     Highlands
    0.75
     Secondary
    0.75
    shire
    0.74
    foundland
    0.72
    Activations Density 0.033%

    No Known Activations