© 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. 6-RES-JB
    11. 7477
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, especially those characterized by long-lasting symptoms or effects

    oai_token-act-pair · gpt-3.5-turbo

    references to chronic health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.91
    */(
    -0.87
    ertodd
    -0.81
    animous
    -0.72
    imov
    -0.72
    govtrack
    -0.72
    ĪĴ
    -0.72
    hammad
    -0.70
    imates
    -0.69
    ansk
    -0.69
    POSITIVE LOGITS
     traumatic
    0.89
    led
    0.86
     inflammation
    0.81
     diseases
    0.80
    ling
    0.80
    pain
    0.77
     disease
    0.75
     homelessness
    0.75
    enegger
    0.74
     chronic
    0.73
    Activations Density 0.027%

    No Known Activations