© 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. 7-RES-JB
    11. 8758
    Prev
    Next
    INDEX
    Explanations

    words related to health issues, especially obesity and related conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to obesity and related health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sky
    -0.82
    oral
    -0.80
     Pon
    -0.74
    ovie
    -0.73
    krit
    -0.72
    gency
    -0.70
    assian
    -0.70
    office
    -0.70
    semble
    -0.69
    private
    -0.68
    POSITIVE LOGITS
     obesity
    1.09
     Obesity
    0.98
     stigma
    0.90
    rition
    0.88
    esity
    0.87
     metabol
    0.86
     prevalence
    0.85
     obese
    0.85
     overweight
    0.83
     tissue
    0.82
    Activations Density 0.031%

    No Known Activations