© 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. 11-RES-JB
    11. 5710
    Prev
    Next
    INDEX
    Explanations

    mentions of things being surprising or noteworthy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "even"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    rend
    -0.93
    aim
    -0.71
    unity
    -0.69
    ugal
    -0.68
    utra
    -0.68
    ============
    -0.68
    asy
    -0.67
    ========
    -0.67
    ĺħ
    -0.66
    warts
    -0.65
    POSITIVE LOGITS
     though
    1.02
     tho
    0.97
    handedly
    0.89
     joked
    0.87
     worse
    0.82
     managed
    0.82
    handed
    0.80
     resorted
    0.80
     remotely
    0.80
     contemplated
    0.78
    Activations Density 0.052%

    No Known Activations