© 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. 8-RES-JB
    11. 21165
    Prev
    Next
    INDEX
    Explanations

    information related to academic degrees, especially Ph.D. titles

    oai_token-act-pair · gpt-3.5-turbo

    references to academic degrees and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TMZ
    -0.81
    phant
    -0.69
     Clan
    -0.68
     comfort
    -0.66
     Crom
    -0.65
    ãĥ´ãĤ¡
    -0.63
     Apex
    -0.63
     inconven
    -0.62
    ãĥ«
    -0.62
     Jericho
    -0.62
    POSITIVE LOGITS
     dissertation
    1.42
     thesis
    1.28
    ploma
    1.26
     Degree
    1.14
    ertation
    1.11
     doctoral
    1.00
     degree
    0.99
    uates
    0.98
     diploma
    0.97
    achelor
    0.95
    Activations Density 0.074%

    No Known Activations