© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10376
    Prev
    Next
    INDEX
    Explanations

    terms related to universities and academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of universities and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worthiness
    -0.74
    ãĥ©
    -0.74
    è¦ļéĨĴ
    -0.66
    finder
    -0.65
    orders
    -0.64
    arding
    -0.63
    range
    -0.62
    obin
    -0.62
    ichick
    -0.61
    tera
    -0.61
    POSITIVE LOGITS
     faculty
    1.58
     Faculty
    1.49
     University
    1.45
     undergrad
    1.40
     Students
    1.38
     professors
    1.35
     undergraduate
    1.34
     students
    1.33
     graduate
    1.31
     College
    1.31
    Activations Density 0.285%

    No Known Activations