© 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. 7-RES-JB
    11. 17276
    Prev
    Next
    INDEX
    Explanations

    names of universities and educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.72
    eur
    -0.68
    requ
    -0.64
     totem
    -0.63
     festive
    -0.62
     smugglers
    -0.61
    odic
    -0.61
     filler
    -0.60
    meaning
    -0.60
    elist
    -0.60
    POSITIVE LOGITS
     University
    1.64
    University
    1.32
     faculty
    1.18
     Faculty
    1.15
     Institution
    1.06
     universities
    1.06
     Univ
    1.06
     College
    1.01
     Libraries
    1.00
     Universities
    0.99
    Activations Density 0.133%

    No Known Activations