© 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. 4-RES-JB
    11. 4910
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States of America or things related to America

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "American."

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

    No Comments

    Negative Logits
    fill
    -0.76
    fm
    -0.74
    Fill
    -0.72
    theless
    -0.69
    order
    -0.69
    ogyn
    -0.69
    COLOR
    -0.68
    ologically
    -0.67
    ĵĺ
    -0.67
    spring
    -0.66
    POSITIVE LOGITS
     Embassy
    1.01
     embassy
    1.00
     Samoa
    0.96
     Airlines
    0.95
     embassies
    0.90
     Expedition
    0.87
     consulate
    0.86
     diplomats
    0.84
     ambassador
    0.82
     exile
    0.81
    Activations Density 0.039%

    No Known Activations