© 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. 3-RES-JB
    11. 658
    Prev
    Next
    INDEX
    Explanations

    words related to mental health conditions, specifically focusing on depression

    oai_token-act-pair · gpt-3.5-turbo

    references to depression and its related conditions

    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
    Sources
    -0.94
    Reply
    -0.81
    Grab
    -0.79
    source
    -0.77
    tnc
    -0.77
    leon
    -0.75
    SPONSORED
    -0.73
    quer
    -0.72
    xxxxxxxx
    -0.70
    Member
    -0.69
    POSITIVE LOGITS
     depression
    1.10
     relapse
    0.89
     depressive
    0.87
     Depression
    0.83
     disorder
    0.81
     medication
    0.79
     diagnosis
    0.79
     distress
    0.77
     depress
    0.76
     worsen
    0.76
    Activations Density 0.014%

    No Known Activations