© 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. 11-RES-JB
    11. 23041
    Prev
    Next
    INDEX
    Explanations

    mentions of specific nationalities or ethnic groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uria
    -0.78
    ellation
    -0.73
    ossession
    -0.73
    thora
    -0.72
    eanor
    -0.71
    olester
    -0.71
     Topic
    -0.70
     Archdemon
    -0.68
    llor
    -0.67
    tesy
    -0.67
    POSITIVE LOGITS
     staffers
    1.29
     journalists
    1.23
     professionals
    1.23
     interns
    1.22
     secretaries
    1.22
     businessmen
    1.21
     academics
    1.21
     lawyers
    1.21
     employees
    1.21
     retirees
    1.20
    Activations Density 0.283%

    No Known Activations