© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20462
    Prev
    Next
    INDEX
    Explanations

    country names, particularly the United States and United Kingdom

    oai_token-act-pair · gpt-3.5-turbo

    names of countries and cities, particularly emphasizing the term "United."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ————
    -0.61
     âĻ
    -0.60
     notation
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.56
     these
    -0.55
     "<
    -0.55
     overt
    -0.54
     âĸº
    -0.54
     unde
    -0.54
    ****************
    -0.54
    POSITIVE LOGITS
    foundland
    0.76
    etheless
    0.70
    luaj
    0.62
     Hudson
    0.60
    é¾įåĸļ士
    0.58
    esses
    0.58
    amins
    0.57
     Strait
    0.56
    taboola
    0.55
    odium
    0.55
    Activations Density 0.415%

    No Known Activations