© 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. 12642
    Prev
    Next
    INDEX
    Explanations

    political statements or controversies involving provocative or inflammatory language

    oai_token-act-pair · gpt-3.5-turbo

    pejorative or controversial statements made about individuals or 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
    utic
    -0.91
    folio
    -0.88
    byss
    -0.84
    sbm
    -0.81
    ETF
    -0.80
    utical
    -0.77
    ngth
    -0.77
    catentry
    -0.76
    -|
    -0.75
    kj
    -0.74
    POSITIVE LOGITS
     Mexicans
    1.49
     gays
    1.46
     homosexuals
    1.44
     Muslims
    1.38
     homosexuality
    1.37
     Adolf
    1.33
     Jews
    1.30
     rapists
    1.26
     Islam
    1.22
     rape
    1.21
    Activations Density 0.436%

    No Known Activations