© 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. 3-RES-JB
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    words related to chronic medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to chronic conditions or illnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -1.02
    ramid
    -0.92
    hammad
    -0.83
    ansk
    -0.82
    cius
    -0.75
    animous
    -0.73
    ertodd
    -0.73
    govtrack
    -0.72
    wagen
    -0.72
    imates
    -0.71
    POSITIVE LOGITS
     chronic
    0.80
    led
    0.77
     inflammation
    0.75
     traumatic
    0.73
     Chronic
    0.72
     diseases
    0.72
    pain
    0.71
    ãĥ¥
    0.70
     maintenance
    0.70
     fatigue
    0.69
    Activations Density 0.010%

    No Known Activations