© 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. 5239
    Prev
    Next
    INDEX
    Explanations

    settings or options that can be turned on or off

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and phrases related to settings or options in software configurations

    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
    esta
    -0.76
    uggets
    -0.73
    issance
    -0.72
    bris
    -0.71
     Rus
    -0.69
    axies
    -0.69
     reprint
    -0.68
     Bib
    -0.68
    llah
    -0.66
    arians
    -0.66
    POSITIVE LOGITS
     Enabled
    1.48
    Enabled
    1.43
    Enable
    1.39
    disable
    1.38
     disable
    1.37
     Disable
    1.37
     enabled
    1.36
     Enable
    1.34
    Disable
    1.34
    disabled
    1.33
    Activations Density 0.324%

    No Known Activations