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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16661
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "American" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to American culture and identity

    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
    */(
    -0.75
    heed
    -0.73
    orders
    -0.68
    RH
    -0.67
    razil
    -0.67
    NB
    -0.66
    aird
    -0.64
    _>
    -0.63
     KR
    -0.62
    order
    -0.61
    POSITIVE LOGITS
     Airlines
    1.20
     Samoa
    1.15
     Idol
    1.05
    ICAN
    0.94
     Express
    0.94
    icus
    0.90
     Sniper
    0.88
     Indians
    0.86
    ized
    0.85
     Horror
    0.85
    Activations Density 0.067%

    No Known Activations