© 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. 4-RES-JB
    11. 6854
    Prev
    Next
    INDEX
    Explanations

    names of people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    names of people, specifically those in entertainment or culture

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

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.54
     glim
    -0.51
    Reviewer
    -0.49
    DonaldTrump
    -0.48
    âĸĵ
    -0.48
     NETWORK
    -0.47
    BOOK
    -0.46
    20439
    -0.45
     prompt
    -0.44
     bulletin
    -0.44
    POSITIVE LOGITS
     respectively
    0.57
    )|
    0.57
    anas
    0.53
    ande
    0.50
    )]
    0.48
    ado
    0.47
    ys
    0.47
    anus
    0.46
    tis
    0.45
    )--
    0.45
    Activations Density 1.762%

    No Known Activations