© 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. 5088
    Prev
    Next
    INDEX
    Explanations

    words related to legal or criminal activities

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

    specific names associated with events, characters, or titles

    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
     WA
    -0.89
     Kare
    -0.88
     Kate
    -0.86
    Kate
    -0.81
    Ark
    -0.81
     Maher
    -0.80
     Dunham
    -0.78
     Kun
    -0.78
     Kash
    -0.76
     Bowen
    -0.76
    POSITIVE LOGITS
    Nic
    1.52
     Nic
    1.47
     Ric
    1.45
    ic
    1.44
     ric
    1.32
    nic
    1.32
    icc
    1.31
     Cic
    1.30
     ic
    1.29
    IC
    1.28
    Activations Density 0.446%

    No Known Activations