© 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. 0-RES-JB
    11. 9846
    Prev
    Next
    INDEX
    Explanations

    names of individuals named "George."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "George."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢ
    -0.79
     Siren
    -0.71
    cms
    -0.71
     pup
    -0.69
    Login
    -0.66
    arers
    -0.66
     respawn
    -0.66
     tether
    -0.66
    âľ
    -0.65
    entimes
    -0.64
    POSITIVE LOGITS
     George
    3.44
    George
    3.05
     Ronald
    1.66
     Georg
    1.54
     William
    1.48
     Charles
    1.37
     John
    1.37
     Barack
    1.37
     Bush
    1.35
     Edward
    1.33
    Activations Density 0.026%

    No Known Activations