© 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. 1-RES-JB
    11. 20451
    Prev
    Next
    INDEX
    Explanations

    references to the National Health Service (NHS)

    oai_token-act-pair · gpt-3.5-turbo

    references to the National Health Service (NHS)

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    gered
    -0.76
    ========
    -0.72
    ographed
    -0.72
    1963
    -0.67
    iating
    -0.67
     Dag
    -0.64
    nings
    -0.64
    Rod
    -0.64
     Rod
    -0.63
     SPI
    -0.62
    POSITIVE LOGITS
     NHS
    1.00
    aceutical
    0.96
    earch
    0.91
    krit
    0.87
     healthcare
    0.85
    yth
    0.82
     traged
    0.82
    avorite
    0.77
     pse
    0.75
     challeng
    0.74
    Activations Density 0.004%

    No Known Activations