© 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. 12-RES-JB
    11. 5023
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations and misconduct

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to sexual assault and victimization

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     FDR
    -0.90
     bourbon
    -0.90
     cigar
    -0.85
     cigars
    -0.85
     Whitman
    -0.82
     nonpartisan
    -0.81
     Wilmington
    -0.78
     Chevy
    -0.76
     Vermont
    -0.76
     flavor
    -0.75
    POSITIVE LOGITS
    âĢ
    1.13
     CCTV
    1.12
    à¦
    1.09
    Þ
    1.06
    ÄŁ
    1.04
    kaya
    1.01
     counselling
    1.01
    اÙĦ
    1.01
     WhatsApp
    0.99
    ã
    0.97
    Activations Density 1.166%

    No Known Activations