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

    Neuronpedia

    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. 7-RES-JB
    11. 3065
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health disorders, such as ADHD, bipolar disorder, depression, and anxiety

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mental health disorders

    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
     snipp
    -0.73
    stanbul
    -0.70
    din
    -0.67
    riel
    -0.65
    raltar
    -0.64
    externalActionCode
    -0.62
     slic
    -0.62
    ilet
    -0.61
    eworld
    -0.61
    vis
    -0.61
    POSITIVE LOGITS
     diagnoses
    1.05
     diagnosis
    0.98
     symptoms
    0.96
     disorders
    0.92
     Symptoms
    0.92
     Disorders
    0.87
    ipolar
    0.86
     worsen
    0.86
     disorder
    0.85
     worsened
    0.82
    Activations Density 0.045%

    No Known Activations