© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10180
    Prev
    Next
    INDEX
    Explanations

    references to different religious groups in relation to inclusion or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    references to various religious and cultural groups

    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
    forcer
    -0.81
     regulator
    -0.80
    HOME
    -0.79
    forcement
    -0.78
    advertisement
    -0.76
    gency
    -0.74
    ellation
    -0.72
     advisory
    -0.71
     bidding
    -0.71
     guiActiveUn
    -0.70
    POSITIVE LOGITS
     Asians
    1.68
     Arabs
    1.67
     Italians
    1.63
     Greeks
    1.59
     Jews
    1.58
     Mexicans
    1.58
     Hispanics
    1.57
     Hindus
    1.57
     Muslims
    1.54
     Christians
    1.54
    Activations Density 0.232%

    No Known Activations