© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18983
    Prev
    Next
    INDEX
    Explanations

    academic titles and affiliations, such as professors at universities and experts in specific fields

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to academic affiliations and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙIJ
    -0.91
    pees
    -0.80
    ieties
    -0.77
    zens
    -0.73
    etsy
    -0.70
    inately
    -0.69
    merce
    -0.69
    igg
    -0.69
    oche
    -0.68
    edia
    -0.68
    POSITIVE LOGITS
     chairman
    1.19
     founder
    1.15
     chair
    1.10
     grandson
    1.08
     author
    1.06
     dean
    1.05
     longtime
    1.05
     vice
    1.05
     adjunct
    1.02
     formerly
    1.01
    Activations Density 0.111%

    No Known Activations