© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24060
    Prev
    Next
    INDEX
    Explanations

    negative or offensive terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to online safety and censorship

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Quart
    -0.95
     Lieutenant
    -0.82
     induction
    -0.81
    anship
    -0.80
     ceremonial
    -0.79
    rentices
    -0.78
     apprentices
    -0.76
    Construction
    -0.74
     Clarke
    -0.72
     Assembly
    -0.71
    POSITIVE LOGITS
     spam
    1.49
     URLs
    1.48
     HTTPS
    1.28
     HTTP
    1.22
     websites
    1.21
     malware
    1.20
     browsing
    1.19
     browsers
    1.19
    Content
    1.18
     Gmail
    1.18
    Activations Density 0.921%

    No Known Activations