© 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. 3-RES-JB
    11. 8123
    Prev
    Next
    INDEX
    Explanations

    references to the basketball player "Korver" and variations of the word "Koran"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Korver" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.90
    enegger
    -0.86
    ships
    -0.78
    ãģ¦
    -0.75
    æĢ
    -0.74
    IBLE
    -0.73
    ATURE
    -0.72
     Democr
    -0.71
    ATURES
    -0.71
     Sussex
    -0.69
    POSITIVE LOGITS
     Klux
    1.11
     Kor
    1.08
    anic
    1.07
    onite
    0.92
    ©¶æ
    0.90
    adian
    0.86
    oshenko
    0.85
    anus
    0.84
    ussia
    0.84
    enei
    0.84
    Activations Density 0.012%

    No Known Activations