© 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. 9-RES-JB
    11. 15515
    Prev
    Next
    INDEX
    Explanations

    words related to education and specific organizations or entities like lecturers, universities, and the Postal Service

    oai_token-act-pair · gpt-3.5-turbo

    the end of sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ned
    -0.77
    ivari
    -0.72
    odka
    -0.71
    ague
    -0.68
    nor
    -0.67
    aban
    -0.66
    witz
    -0.65
    ivot
    -0.65
    lda
    -0.65
    itably
    -0.65
    POSITIVE LOGITS
    ging
    0.82
    uring
    0.79
    gers
    0.78
    lishing
    0.77
    deen
    0.74
    ificantly
    0.73
    ilant
    0.73
    urous
    0.73
    sis
    0.72
    ures
    0.70
    Activations Density 0.135%

    No Known Activations