© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9369
    Prev
    Next
    INDEX
    Explanations

    references to nationalities and places

    oai_token-act-pair · gpt-3.5-turbo

    words related to nationalities and ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raviolet
    -0.86
    oyer
    -0.85
    acebook
    -0.79
    idious
    -0.78
    utherford
    -0.77
    urer
    -0.75
    lished
    -0.75
    ullivan
    -0.74
    abus
    -0.74
    umbnails
    -0.74
    POSITIVE LOGITS
    istan
    1.13
     nationals
    1.01
     Airways
    0.97
     Nadu
    0.92
     Airlines
    0.91
    istani
    0.91
    apolis
    0.89
     Affairs
    0.88
     embassy
    0.81
     exile
    0.81
    Activations Density 0.062%

    No Known Activations