© 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. 2243
    Prev
    Next
    INDEX
    Explanations

    forms asking for email addresses

    oai_token-act-pair · gpt-3.5-turbo

    elements related to email entry and validation in forms

    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
    bler
    -0.68
    ²
    -0.60
    aris
    -0.59
    aroo
    -0.59
    xit
    -0.58
    STD
    -0.57
    alore
    -0.56
    obyl
    -0.56
    lag
    -0.55
    road
    -0.55
    POSITIVE LOGITS
     Javascript
    0.82
    Email
    0.79
     javascript
    0.78
    ername
    0.75
    acters
    0.69
     email
    0.67
    email
    0.66
    Password
    0.65
    submit
    0.64
     Email
    0.63
    Activations Density 0.019%

    No Known Activations