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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2736
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and diseases, specifically focusing on obesity and its associated risks and effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obesity and its various implications

    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
     VIS
    -0.75
    ×Ļ×
    -0.72
     CFR
    -0.71
    voy
    -0.71
     Pon
    -0.71
    une
    -0.70
    sky
    -0.69
    source
    -0.68
     RPM
    -0.68
     PBS
    -0.68
    POSITIVE LOGITS
     obesity
    1.35
    esity
    1.13
     obese
    1.02
     tremend
    0.97
     Obesity
    0.95
     overweight
    0.88
    ailability
    0.85
     ove
    0.82
     metabolism
    0.82
     tiss
    0.82
    Activations Density 0.005%

    No Known Activations