© 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. 21755
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and entities related to the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States in various contexts

    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
    struct
    -0.67
    Transfer
    -0.66
    ĪĴ
    -0.66
    rious
    -0.65
    iosyn
    -0.63
    warts
    -0.62
    Vote
    -0.61
    ighters
    -0.61
    ãĤ¦ãĤ¹
    -0.61
     captains
    -0.60
    POSITIVE LOGITS
     Midwest
    0.92
     mainland
    0.91
     countryside
    0.86
     Alps
    0.84
     marketplace
    0.84
     Patent
    0.83
     Isles
    0.82
     vicinity
    0.80
     illegally
    0.78
     Territories
    0.78
    Activations Density 0.101%

    No Known Activations