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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    phrases related to depression and emotional suppression

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional states and their relationship with consumption, particularly concerning chocolate and depression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 11 - sadness

    No Comments

    Negative Logits
    pedia
    -0.89
    Forge
    -0.83
     Zup
    -0.79
    Register
    -0.78
    ultan
    -0.78
    Leg
    -0.77
    uthor
    -0.77
    rentices
    -0.76
    wana
    -0.76
    ansky
    -0.76
    POSITIVE LOGITS
     sadness
    1.87
     emotions
    1.64
     sorrow
    1.61
     melancholy
    1.57
     emotion
    1.56
     melanch
    1.56
     depressed
    1.55
     emotional
    1.54
     feelings
    1.52
     depressive
    1.52
    Activations Density 0.562%

    No Known Activations