© 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. 10-RES-JB
    11. 16605
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Andrew

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Andrew" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igi
    -0.73
    ingen
    -0.70
    ioned
    -0.69
    naire
    -0.68
    pmwiki
    -0.68
    stice
    -0.67
    PLA
    -0.66
    pointer
    -0.65
    leaders
    -0.64
    hips
    -0.64
    POSITIVE LOGITS
     Mellon
    0.95
     Dice
    0.88
     Gerr
    0.87
     Cuomo
    0.85
     Wiggins
    0.85
     Garfield
    0.84
     Ng
    0.83
     Sullivan
    0.82
     McMahon
    0.82
     Jackson
    0.82
    Activations Density 0.022%

    No Known Activations