© 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. 24293
    Prev
    Next
    INDEX
    Explanations

    individuals or groups mentioned as signatories or participants in official documents or agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to formal group affiliations or endorsements

    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
    士
    -0.76
    Recipe
    -0.75
    Url
    -0.71
    é»Ĵ
    -0.70
    ungle
    -0.69
    bringer
    -0.69
    sis
    -0.68
    direction
    -0.68
     decay
    -0.67
     discrepancy
    -0.67
    POSITIVE LOGITS
     representatives
    1.21
     dozens
    1.06
     fellow
    1.05
     mayors
    1.01
     members
    0.99
     colleagues
    0.99
     collaborators
    0.99
     celebrities
    0.98
     allies
    0.97
     businessmen
    0.96
    Activations Density 0.359%

    No Known Activations