© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological assessment and medical surveys

    oai_token-act-pair · gpt-3.5-turbo

    references to questionnaires and assessments related to autism traits and social responsiveness

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mehran
    -0.85
    Lago
    -0.78
     Rove
    -0.74
    mare
    -0.71
    ctuary
    -0.70
    ghai
    -0.69
    Tour
    -0.68
    pora
    -0.65
     racket
    -0.64
     untold
    -0.64
    POSITIVE LOGITS
     subsc
    1.50
     questionnaire
    1.45
     DSM
    1.25
     checklist
    1.25
     criteria
    1.24
     criterion
    1.15
     diagnostic
    1.13
    naires
    1.11
     assessments
    1.11
     standardized
    1.06
    Activations Density 0.245%

    No Known Activations