© 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. 11-RES-JB
    11. 15028
    Prev
    Next
    INDEX
    Explanations

    email-related instructions and content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email subscriptions and related notifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    uras
    -0.65
    naire
    -0.58
    factor
    -0.55
     Painter
    -0.54
     Tsukuyomi
    -0.53
    istan
    -0.53
    alore
    -0.53
    umin
    -0.53
    ËĪ
    -0.53
    llan
    -0.53
    POSITIVE LOGITS
     emails
    0.96
     Emails
    0.76
     invitations
    0.70
     notifications
    0.68
     email
    0.68
    interstitial
    0.66
     newsletters
    0.64
    email
    0.62
    icka
    0.59
     messages
    0.59
    Activations Density 0.016%

    No Known Activations