© 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. 7-RES-JB
    11. 2206
    Prev
    Next
    INDEX
    Explanations

    mentions of European nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or ethnicities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odder
    -0.86
    icago
    -0.85
    nyder
    -0.85
    utherford
    -0.84
    ertodd
    -0.83
    affles
    -0.81
    mble
    -0.81
    iscons
    -0.79
    ividual
    -0.79
    uder
    -0.78
    POSITIVE LOGITS
    oslov
    0.98
     Nadu
    0.89
     nationals
    0.88
     shepherd
    0.84
     translation
    0.83
     cuisine
    0.82
     accent
    0.81
     proverb
    0.81
     Portuguese
    0.79
    istani
    0.78
    Activations Density 0.139%

    No Known Activations