© 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. 6-RES-JB
    11. 1036
    Prev
    Next
    INDEX
    Explanations

    references to the name "George"

    oai_token-act-pair · gpt-3.5-turbo

    the name "George" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igslist
    -0.84
    ansas
    -0.75
    endant
    -0.74
    odcast
    -0.74
    lain
    -0.72
    odied
    -0.70
    letal
    -0.69
    ointed
    -0.69
    alty
    -0.69
    pees
    -0.68
    POSITIVE LOGITS
     Orwell
    0.87
     Zimmerman
    0.84
     Thor
    0.82
     Lucas
    0.78
     Georg
    0.77
     Soros
    0.76
     Cic
    0.74
     Whites
    0.73
     Clo
    0.72
     Kru
    0.72
    Activations Density 0.026%

    No Known Activations