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. 7323
    Prev
    Next
    INDEX
    Explanations

    words related to a specific cultural group or location

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and names related to place and geography

    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
    sheet
    -1.03
    ensibly
    -0.78
    riers
    -0.77
    ulent
    -0.76
    sheets
    -0.75
    tracks
    -0.74
    quickShipAvailable
    -0.73
    ensible
    -0.72
    idious
    -0.72
    mort
    -0.71
    POSITIVE LOGITS
     County
    1.36
     Peninsula
    1.36
     Islands
    1.23
     Falls
    1.23
     Valley
    1.15
     Pradesh
    1.14
     Island
    1.12
     River
    1.12
     Tribe
    1.11
     Basin
    1.10
    Activations Density 0.175%

    No Known Activations