© 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. 11-RES-JB
    11. 4738
    Prev
    Next
    INDEX
    Explanations

    mentions of media outlets and publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of major news organizations and media outlets

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    irez
    -0.75
     bonding
    -0.72
    birds
    -0.71
    agara
    -0.68
    arbon
    -0.66
    bender
    -0.64
     tal
    -0.63
     reversible
    -0.63
     mats
    -0.62
     fung
    -0.62
    POSITIVE LOGITS
     Newsweek
    1.36
     Huffington
    1.29
     MSNBC
    1.28
     Politico
    1.23
     CNBC
    1.22
     CNN
    1.21
     NYT
    1.19
     Economist
    1.16
     Salon
    1.15
     NPR
    1.14
    Activations Density 0.117%

    No Known Activations