© 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. 12-RES-JB
    11. 4206
    Prev
    Next
    INDEX
    Explanations

    terms related to education and teachers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to teachers and educational professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    rils
    -0.73
    ose
    -0.73
    ategory
    -0.73
    osher
    -0.70
    Ec
    -0.69
    rencies
    -0.69
    hawks
    -0.69
    axy
    -0.68
     Launcher
    -0.66
    edia
    -0.66
    POSITIVE LOGITS
     unions
    1.15
     Teachers
    1.09
     teachers
    1.08
     teacher
    1.05
     teaching
    0.98
     educators
    0.97
     assistants
    0.96
     Teacher
    0.96
     instructors
    0.94
     superintendent
    0.90
    Activations Density 0.076%

    No Known Activations