© 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 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. 0-RES-JB
    11. 13486
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions, specifically schools

    oai_token-act-pair · gpt-3.5-turbo

    mentions of educational institutions or schools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nod
    -0.68
     metadata
    -0.67
     avail
    -0.66
     lin
    -0.63
     vul
    -0.63
    pez
    -0.63
    lly
    -0.63
    FILE
    -0.62
     tou
    -0.62
    liner
    -0.62
    POSITIVE LOGITS
     School
    3.70
    School
    2.91
     SCHOOL
    2.55
     Schools
    2.53
    school
    2.40
     school
    2.32
     schools
    1.88
     Faculty
    1.70
    College
    1.69
     College
    1.67
    Activations Density 0.017%

    No Known Activations