© 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. 11-RES-JB
    11. 1402
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to celebrities, politicians, and popular media figures

    oai_token-act-pair · gpt-3.5-turbo

    names of actors and notable public figures

    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
    oine
    -0.82
    species
    -0.71
    icol
    -0.71
    Ļ½
    -0.69
    common
    -0.66
    é»Ĵ
    -0.66
    ocol
    -0.66
    ItemThumbnailImage
    -0.66
    Ŀ
    -0.66
    cgi
    -0.65
    POSITIVE LOGITS
     Gets
    1.72
     Says
    1.69
     Makes
    1.61
     Releases
    1.55
     Goes
    1.53
     Needs
    1.50
     Takes
    1.45
     Adds
    1.43
     Uses
    1.43
     Talks
    1.42
    Activations Density 0.279%

    No Known Activations