© 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. 3471
    Prev
    Next
    INDEX
    Explanations

    words related to charter schools and educational policy or issues

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

    references to charter schools and related terminology

    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
    pez
    -0.69
    encer
    -0.64
    ovych
    -0.63
    behind
    -0.63
    cloth
    -0.62
    ences
    -0.59
    borough
    -0.59
    alez
    -0.59
    station
    -0.58
    heng
    -0.58
    POSITIVE LOGITS
    ificate
    0.90
     schools
    0.82
     Schools
    0.79
    ific
    0.73
    ism
    0.73
     school
    0.71
    icut
    0.69
    inary
    0.68
    IZE
    0.68
    cut
    0.68
    Activations Density 0.082%

    No Known Activations