© 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. 20417
    Prev
    Next
    INDEX
    Explanations

    references to national symbols and patriotic actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to national events and symbols, particularly the National Anthem and the flag

    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
    onz
    -0.81
     Macro
    -0.81
    enz
    -0.80
    cells
    -0.79
    >>\
    -0.78
    alysis
    -0.76
    iability
    -0.76
    conom
    -0.76
     Consulting
    -0.75
     Pharma
    -0.75
    POSITIVE LOGITS
     commemor
    1.84
     commem
    1.73
     honoring
    1.64
     salute
    1.63
     memorial
    1.56
     commemorate
    1.50
     ceremony
    1.49
     remembrance
    1.49
     monument
    1.46
     symbolism
    1.45
    Activations Density 0.827%

    No Known Activations