© 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. 8-RES-JB
    11. 11862
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions like anxiety and depression

    oai_token-act-pair · gpt-3.5-turbo

    mentions of anxiety and its impact on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endor
    -0.81
    estone
    -0.77
    ingen
    -0.76
    anmar
    -0.74
    estones
    -0.72
    nice
    -0.71
    sites
    -0.69
    ded
    -0.69
    inka
    -0.67
    emark
    -0.66
    POSITIVE LOGITS
     disorders
    1.06
     disorder
    0.98
     provoking
    0.96
     Disorders
    0.86
    xiety
    0.82
     sickness
    0.80
     anxiety
    0.80
     reliever
    0.79
     inducing
    0.78
     illness
    0.77
    Activations Density 0.040%

    No Known Activations