© 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 EvalsExportsinterp-engineNEWAPI 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. 13192
    Prev
    Next
    INDEX
    Explanations

    prompts related to logging in or creating an account

    oai_token-act-pair · gpt-3.5-turbo

    user authentication and account management phrases

    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
     tract
    -0.72
     compile
    -0.64
     compilation
    -0.62
     ult
    -0.62
     Galile
    -0.62
     ears
    -0.61
     tracts
    -0.60
     propagate
    -0.59
     bundled
    -0.58
     enclosed
    -0.58
    POSITIVE LOGITS
     Username
    0.99
     Login
    0.86
     Password
    0.85
    76561
    0.79
    password
    0.77
    login
    0.75
    qus
    0.71
     {*
    0.71
    Login
    0.71
    Password
    0.68
    Activations Density 0.059%

    No Known Activations