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

    Neuronpedia

    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. 2-RES-JB
    11. 1796
    Prev
    Next
    INDEX
    Explanations

    words related to nationalities and countries

    oai_token-act-pair · gpt-3.5-turbo

    words related to national or ethnic identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lest
    -0.84
    lot
    -0.81
    uers
    -0.79
    oots
    -0.77
    lett
    -0.74
    utherford
    -0.74
    rex
    -0.74
    ucc
    -0.72
    Cloud
    -0.72
    oyer
    -0.72
    POSITIVE LOGITS
    istani
    1.20
     nationals
    1.04
     Nadu
    1.01
    istan
    1.00
     Orthodox
    0.89
     nationalist
    0.86
     nationalists
    0.85
     exile
    0.85
     Affairs
    0.83
    apolis
    0.79
    Activations Density 0.074%

    No Known Activations