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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 18677
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Americans" with a focus on various topics and statistics related to the American population

    oai_token-act-pair · gpt-3.5-turbo

    references to Americans and their perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Initialized
    -0.71
    operation
    -0.69
    NB
    -0.69
    selection
    -0.65
    ijk
    -0.65
    ival
    -0.63
     Auckland
    -0.62
    QB
    -0.62
    Drag
    -0.61
    SourceFile
    -0.61
    POSITIVE LOGITS
    ICAN
    0.82
     Idol
    0.75
    ornings
    0.73
     born
    0.71
     citizens
    0.68
    apolis
    0.68
     Dollars
    0.68
     who
    0.68
     Citizens
    0.68
    ervative
    0.68
    Activations Density 0.044%

    No Known Activations