© 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 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. 2-RES-JB
    11. 14760
    Prev
    Next
    INDEX
    Explanations

    words related to health conditions like obesity

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to obesity and overweight conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLSID
    -0.76
     Pon
    -0.75
     Historical
    -0.68
    sky
    -0.68
     Historic
    -0.68
    ovie
    -0.67
    esa
    -0.66
    href
    -0.65
     PBS
    -0.65
    RL
    -0.65
    POSITIVE LOGITS
     obesity
    1.27
     obese
    1.20
     overweight
    1.14
    esity
    1.07
     Obesity
    0.97
     ove
    0.85
     physique
    0.82
     metabol
    0.80
     metabolism
    0.80
     fat
    0.79
    Activations Density 0.014%

    No Known Activations