© 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. 11-RES-JB
    11. 18591
    Prev
    Next
    INDEX
    Explanations

    mentions of teaching or education-related activities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "teach" and its variations, indicating a focus on educational themes

    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
     sidx
    -0.87
    76561
    -0.74
    ãĥ¼ãĥ³
    -0.74
    axy
    -0.73
    ãĤ»
    -0.70
    ablished
    -0.68
    xon
    -0.67
     Ports
    -0.67
    tar
    -0.66
    etheus
    -0.65
    POSITIVE LOGITS
     kids
    1.00
     undergrad
    1.00
     kindergarten
    1.00
     students
    0.95
     youngsters
    0.95
    children
    0.91
    classes
    0.90
     lessons
    0.89
     children
    0.87
     freshmen
    0.85
    Activations Density 0.045%

    No Known Activations