© 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. 10-RES-JB
    11. 8559
    Prev
    Next
    INDEX
    Explanations

    specific religious or ethnic groups

    oai_token-act-pair · gpt-3.5-turbo

    </br> references to ethnic, religious, or racial groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.94
     increments
    -0.77
    yrinth
    -0.76
     srfAttach
    -0.67
    inery
    -0.62
     McDonnell
    -0.62
    Loop
    -0.61
     domain
    -0.61
    ellation
    -0.59
     Sunshine
    -0.59
    POSITIVE LOGITS
     residing
    1.11
     who
    1.10
     living
    1.07
    paces
    1.03
    ervative
    1.03
    ervatives
    1.01
     everywhere
    1.00
     fleeing
    0.94
    '
    0.94
     themselves
    0.94
    Activations Density 0.166%

    No Known Activations