© 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. 3-RES-JB
    11. 16745
    Prev
    Next
    INDEX
    Explanations

    mentions of nationalities or countries

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "ian" associated with national identities or descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McConnell
    -0.77
    utherford
    -0.76
    raviolet
    -0.76
    lot
    -0.74
    lett
    -0.72
    winner
    -0.70
    mble
    -0.67
    lest
    -0.65
    older
    -0.65
     McMaster
    -0.65
    POSITIVE LOGITS
     nationals
    1.05
    istani
    1.04
    istan
    1.02
     Nadu
    1.01
    oslov
    0.90
     Orthodox
    0.89
     Affairs
    0.87
     Airlines
    0.86
     Airways
    0.85
     embassy
    0.85
    Activations Density 0.056%

    No Known Activations