© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2011
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology or digital content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social media and technology interactions

    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
     Tsukuyomi
    -0.68
     probe
    -0.62
     investigation
    -0.61
     Anger
    -0.60
     util
    -0.60
     postp
    -0.60
    HOME
    -0.60
     redes
    -0.60
     msec
    -0.59
    NESS
    -0.59
    POSITIVE LOGITS
    ed
    1.70
    ioned
    1.65
    ned
    1.62
    edly
    1.54
    eled
    1.53
    ered
    1.49
    sed
    1.47
    ivated
    1.46
    ted
    1.45
    ified
    1.41
    Activations Density 1.060%

    No Known Activations