© 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. 4533
    Prev
    Next
    INDEX
    Explanations

    the word "have" followed by words indicating possession, skills, or actions

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

    the phrase "have" in various contexts, indicating possession or obligation

    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
     Reconstruction
    -0.69
     Apart
    -0.60
     Meet
    -0.59
     Balt
    -0.59
     Carnegie
    -0.59
    —-
    -0.58
     MacArthur
    -0.57
     Dah
    -0.55
    **
    -0.55
     Army
    -0.54
    POSITIVE LOGITS
    senal
    0.95
    kell
    0.86
    ActionCode
    0.85
    cloneembedreportprint
    0.82
    StreamerBot
    0.81
    ù
    0.80
    bara
    0.80
    Ĕ
    0.80
    embedreportprint
    0.80
    č
    0.79
    Activations Density 0.053%

    No Known Activations