© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or measurements

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

    numerical quantities or statistics related to populations and demographic changes

    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
     viz
    -0.60
     theirs
    -0.58
    /"
    -0.54
     yours
    -0.54
     somew
    -0.53
     leng
    -0.52
     sparing
    -0.51
     namely
    -0.51
     Unloaded
    -0.50
    hum
    -0.49
    POSITIVE LOGITS
     000
    1.07
     million
    0.99
    %
    0.88
     thousand
    0.87
    ,
    0.83
    million
    0.83
     percent
    0.79
    00000
    0.79
     MILL
    0.73
    è¦ļéĨĴ
    0.73
    Activations Density 0.168%

    No Known Activations