© 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. 7-RES-JB
    11. 1514
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or governmental issues

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or statements of belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .</
    -0.71
    ?).
    -0.68
    .*
    -0.68
    .).
    -0.62
    ayn
    -0.60
    ãĢĤ
    -0.60
    arist
    -0.59
    +.
    -0.59
    .<
    -0.57
    aired
    -0.56
    POSITIVE LOGITS
     [
    0.99
    ,"
    0.92
    ,'"
    0.79
    %"
    0.78
    initely
    0.74
    ,''
    0.73
    ),"
    0.68
     incent
    0.67
     anecd
    0.66
    .,"
    0.65
    Activations Density 0.843%

    No Known Activations