© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 13961
    Prev
    Next
    INDEX
    Explanations

    email verification prompts

    oai_token-act-pair · gpt-3.5-turbo

    prompts related to email entry and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.61
    ccording
    -0.61
    è¦ļéĨĴ
    -0.59
     chopping
    -0.55
     promul
    -0.53
    eatures
    -0.53
     declass
    -0.52
    senal
    -0.50
     tremend
    -0.50
    idious
    -0.50
    POSITIVE LOGITS
    prise
    0.78
    tainment
    0.65
    ãĤº
    0.60
    xon
    0.58
     isEnabled
    0.58
    forge
    0.58
     Latvia
    0.58
    iframe
    0.58
    myra
    0.57
    prises
    0.56
    Activations Density 0.007%

    No Known Activations