© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4394
    Prev
    Next
    INDEX
    Explanations

    phrases related to work or professional interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the mention of specific individuals and events related to political or social news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢij
    -0.96
     nineteen
    -0.92
     eighteen
    -0.83
    ,[
    -0.73
     eighty
    -0.72
     ninety
    -0.71
     sixteen
    -0.71
     nineteenth
    -0.70
     fourteen
    -0.69
    ertodd
    -0.69
    POSITIVE LOGITS
     @
    1.69
     pic
    1.43
     #
    1.42
     https
    1.29
    .#
    1.28
    ðŁ
    1.25
     ðŁij
    1.24
     ðŁ
    1.22
     "@
    1.22
    ðŁĺ
    1.20
    Activations Density 1.471%

    No Known Activations