© 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. 0-RES-JB
    11. 1892
    Prev
    Next
    INDEX
    Explanations

    the word "ve", which is likely short for "have"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ignition
    -0.64
     Rhod
    -0.64
     Calculator
    -0.61
     Springer
    -0.61
     Izan
    -0.60
     fractions
    -0.59
     largeDownload
    -0.58
     datas
    -0.58
     Alert
    -0.57
    è¦ļéĨĴ
    -0.57
    POSITIVE LOGITS
    ve
    4.39
    ves
    2.24
    VE
    2.19
    ved
    2.06
    Ve
    1.86
    ving
    1.81
    vell
    1.78
    vet
    1.72
    vo
    1.56
    vel
    1.53
    Activations Density 0.038%

    No Known Activations