© 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. 22957
    Prev
    Next
    INDEX
    Explanations

    mentions of African-American identity or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to the African American community

    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
     Shutterstock
    -0.84
    pload
    -0.75
     Dickinson
    -0.70
     Pastebin
    -0.70
     shutter
    -0.68
     Prol
    -0.65
     shovel
    -0.65
    igslist
    -0.65
    orious
    -0.63
     execut
    -0.62
    POSITIVE LOGITS
    American
    1.22
    Americans
    1.11
    themed
    1.09
    origin
    1.07
    sounding
    1.06
    inspired
    1.05
    dominated
    1.02
    based
    1.01
    derived
    1.00
    speaking
    1.00
    Activations Density 0.057%

    No Known Activations