Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8625
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to weight, specifically obesity

    oai_token-act-pair · gpt-3.5-turbo

    references to obesity and related terms

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

    No Comments

    Negative Logits
    sky
    -0.79
     Pon
    -0.74
    href
    -0.74
    ership
    -0.74
     Glas
    -0.73
    assian
    -0.71
    esa
    -0.71
    ×Ļ×
    -0.69
    uncture
    -0.68
    leon
    -0.67
    POSITIVE LOGITS
     obesity
    1.24
     Obesity
    1.03
     obese
    1.02
     overweight
    0.97
    esity
    0.96
     metabol
    0.93
     metabolism
    0.88
     epidemic
    0.88
    rition
    0.84
     stigma
    0.80
    Activations Density 0.008%

    No Known Activations