© 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. 11-RES-JB
    11. 20762
    Prev
    Next
    INDEX
    Explanations

    keywords related to professions or professional activities

    oai_token-act-pair · gpt-3.5-turbo

    references to professional roles and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.75
    anus
    -0.73
    erella
    -0.71
    apo
    -0.71
    stant
    -0.71
    enos
    -0.69
    MORE
    -0.67
    orious
    -0.67
    rir
    -0.65
    ource
    -0.65
    POSITIVE LOGITS
     wrestler
    1.21
     athlete
    1.10
    ized
    1.08
     wrestling
    1.06
     athletes
    1.03
     footballer
    1.02
    ization
    1.02
    ising
    1.00
    izing
    0.98
     gol
    0.96
    Activations Density 0.033%

    No Known Activations