© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12862
    Prev
    Next
    INDEX
    Explanations

    instructions related to email address validation

    oai_token-act-pair · gpt-3.5-turbo

    validation errors related to email addresses

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ccording
    -0.65
     conduc
    -0.53
     Assassins
    -0.52
     HG
    -0.52
     tremend
    -0.49
     Cosponsors
    -0.49
     Kats
    -0.48
     eleph
    -0.47
     conclud
    -0.47
     nom
    -0.47
    POSITIVE LOGITS
    iframe
    0.70
    taboola
    0.70
    Ñı
    0.68
    Invalid
    0.67
     Invalid
    0.66
    Wr
    0.65
     Please
    0.62
    px
    0.60
    REDACTED
    0.58
    dayName
    0.58
    Activations Density 0.025%

    No Known Activations