© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2873
    Prev
    Next
    INDEX
    Explanations

    mentions related to the National Health Service (NHS)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of "the NHS" and related references to healthcare

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    milo
    -0.90
    obos
    -0.83
    oops
    -0.83
    inel
    -0.81
    atl
    -0.81
    SAN
    -0.75
    odon
    -0.74
    reads
    -0.74
    verson
    -0.74
    externalActionCode
    -0.74
    POSITIVE LOGITS
     UK
    1.29
     Midlands
    1.28
     Isle
    1.19
     Highlands
    1.19
     NHS
    1.16
     Isles
    1.14
     Welsh
    1.09
     countryside
    1.06
     Thames
    1.05
     Clyde
    1.05
    Activations Density 0.243%

    No Known Activations