© 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. 3-RES-JB
    11. 12723
    Prev
    Next
    INDEX
    Explanations

    keywords related to online accounts, including creating, logging in, or deleting them, as well as specific platforms like Facebook and Google

    oai_token-act-pair · gpt-3.5-turbo

    references to social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.81
    RAY
    -0.72
    GGGGGGGG
    -0.67
     Jinn
    -0.66
     Sight
    -0.63
     spur
    -0.63
    trap
    -0.61
     Fulton
    -0.60
     cure
    -0.60
     Springer
    -0.60
    POSITIVE LOGITS
     balances
    1.05
    ancy
    1.03
     accounts
    0.97
    abilities
    0.95
    Account
    0.93
    ants
    0.92
    account
    0.90
     account
    0.88
     username
    0.87
     rece
    0.82
    Activations Density 0.016%

    No Known Activations