© 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. 9-RES-JB
    11. 20714
    Prev
    Next
    INDEX
    Explanations

    mentions of different nationalities or political affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities and ethnicities, particularly in the context of American and Middle Eastern identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologies
    -1.03
    bows
    -1.02
    ravings
    -1.02
    ories
    -1.00
    rils
    -0.92
    acies
    -0.91
    abilities
    -0.91
    encies
    -0.90
    onies
    -0.88
    isites
    -0.87
    POSITIVE LOGITS
     who
    1.09
     citizen
    1.07
     politician
    1.03
     woman
    1.01
     colleague
    1.00
     traveler
    1.00
     thinker
    0.98
     traveller
    0.96
     journalist
    0.95
     believer
    0.94
    Activations Density 0.260%

    No Known Activations