© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal processes and government bodies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" indicating the presence of entities or statuses in a legal or formal context

    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
     Verd
    -0.78
    ossom
    -0.75
    Afee
    -0.75
    antz
    -0.73
     IMAGES
    -0.71
    vantage
    -0.67
    vec
    -0.65
     Highlights
    -0.64
    ulence
    -0.63
    rave
    -0.63
    POSITIVE LOGITS
     tasked
    1.38
     convened
    1.24
     empowered
    1.23
     staffed
    1.20
     obligated
    1.20
     appointed
    1.17
     chaired
    1.17
     nonpartisan
    1.15
     powerless
    1.13
     obliged
    1.11
    Activations Density 0.229%

    No Known Activations