© 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. 9-RES-JB
    11. 2260
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and related concepts

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĥķãĤ©
    -0.84
    ãĥĥãĤ¯
    -0.76
    bugs
    -0.75
    ãĥīãĥ©ãĤ´ãĥ³
    -0.74
     è£ıç
    -0.73
    ãĥ¢
    -0.72
    pects
    -0.70
    usercontent
    -0.70
    Delete
    -0.70
    çIJ
    -0.69
    POSITIVE LOGITS
    college
    1.43
     university
    1.39
     graduate
    1.30
     colleges
    1.29
     vocational
    1.28
     college
    1.26
     scholarship
    1.24
     universities
    1.24
    graduate
    1.22
    school
    1.21
    Activations Density 0.207%

    No Known Activations