© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    people's names, specifically the name "Crist" in various formats

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Crist

    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
    RAW
    -0.75
    alpha
    -0.69
     alpha
    -0.66
     selector
    -0.62
     delta
    -0.62
    osure
    -0.62
    appa
    -0.61
     Peel
    -0.60
     freedoms
    -0.60
    Bomb
    -0.60
    POSITIVE LOGITS
     Crist
    3.87
     Ronaldo
    1.30
     Kry
    1.19
    Krist
    1.19
     Gian
    1.13
    cia
    1.13
     Sark
    1.09
     Jac
    1.08
     Krist
    1.08
     Carlo
    1.07
    Activations Density 0.019%

    No Known Activations