© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13147
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Joel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Joel."

    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
    utils
    -0.73
     circ
    -0.69
    FACE
    -0.68
    dayName
    -0.67
    BOOK
    -0.65
    stroke
    -0.64
    hib
    -0.63
     parity
    -0.63
    system
    -0.63
    bred
    -0.63
    POSITIVE LOGITS
     Joel
    1.02
    aquin
    0.90
     Wein
    0.87
     McH
    0.85
     Goodman
    0.84
    lee
    0.81
    lein
    0.79
    Lens
    0.79
     Dixon
    0.78
     Klein
    0.75
    Activations Density 0.005%

    No Known Activations