© 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. 10-RES-JB
    11. 3011
    Prev
    Next
    INDEX
    Explanations

    options or choices presented to the reader

    oai_token-act-pair · gpt-3.5-turbo

    options and alternatives for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocracy
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    Therefore
    -0.71
    ulner
    -0.71
    ptoms
    -0.71
    agonists
    -0.69
    hed
    -0.66
    eness
    -0.64
    ocratic
    -0.63
    tnc
    -0.63
    POSITIVE LOGITS
     alternatively
    1.43
     browse
    1.17
     download
    1.06
    chard
    0.99
     subscribe
    0.98
    acle
    0.95
     customize
    0.93
    lando
    0.92
     choose
    0.91
     donate
    0.90
    Activations Density 0.099%

    No Known Activations