© 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. 10-RES-JB
    11. 13704
    Prev
    Next
    INDEX
    Explanations

    people with academic or professional titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to academic and professional positions

    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
     Blacks
    -0.67
     Hague
    -0.67
     Beasts
    -0.63
    attacks
    -0.62
    rums
    -0.58
     bathrooms
    -0.58
     Carnage
    -0.57
    veyard
    -0.57
     cloves
    -0.57
    ems
    -0.57
    POSITIVE LOGITS
     member
    0.92
     of
    0.92
     specializing
    0.90
     aboard
    0.85
     at
    0.83
     Fellow
    0.82
     attending
    0.78
     advisor
    0.77
     adviser
    0.75
     studying
    0.74
    Activations Density 0.153%

    No Known Activations