© 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. 11-RES-JB
    11. 10037
    Prev
    Next
    INDEX
    Explanations

    references to countries, especially the United States

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United States in relation to various topics

    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
    rious
    -0.69
    lets
    -0.65
    msg
    -0.64
    Transfer
    -0.61
    Jump
    -0.61
    errors
    -0.61
    enance
    -0.61
    eus
    -0.61
    ãĤ¦ãĤ¹
    -0.59
    cler
    -0.59
    POSITIVE LOGITS
     Midwest
    1.09
     mainland
    1.08
     Territories
    0.95
     Postal
    0.89
     Isles
    0.88
     Alps
    0.87
     Patent
    0.86
     economy
    0.85
     Midlands
    0.85
     market
    0.85
    Activations Density 0.089%

    No Known Activations