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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3771
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions, especially "Mayo Clinic"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of medical institutions and related individuals

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

    No Comments

    Negative Logits
    LIST
    -0.70
    eworld
    -0.70
     sqor
    -0.69
    izations
    -0.69
    Jew
    -0.68
    ship
    -0.67
    wig
    -0.66
     Colonial
    -0.63
     Kali
    -0.63
    culosis
    -0.63
    POSITIVE LOGITS
     Mayo
    1.36
     Clinic
    1.17
    ousy
    0.85
    xon
    0.85
    aspberry
    0.84
    onen
    0.79
    Downloadha
    0.79
    osate
    0.79
    olicy
    0.79
    ás
    0.78
    Activations Density 0.010%

    No Known Activations