© 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. 8-RES-JB
    11. 2185
    Prev
    Next
    INDEX
    Explanations

    legal terms related to discrimination and inappropriate behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with controversial and inflammatory political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    Fires individually on " unlawfully", " disorderly", " impair", " posessing", " oneself", " willfully", "ossession"

    No Comments

    Negative Logits
     Seym
    -0.72
     Krug
    -0.68
     Barney
    -0.68
     Bravo
    -0.67
     Omaha
    -0.64
     Cassidy
    -0.62
     Rudy
    -0.62
     Nieto
    -0.61
     Sahara
    -0.60
     Blueprint
    -0.60
    POSITIVE LOGITS
     persons
    0.86
     prohibited
    0.86
     specified
    0.84
     lawful
    0.84
     unlawfully
    0.83
     hereby
    0.80
     shall
    0.80
     unlawful
    0.80
     lawfully
    0.79
     Persons
    0.79
    Activations Density 1.092%

    No Known Activations