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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2694
    Prev
    Next
    INDEX
    Explanations

    famous names, especially ones related to sports and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    names of famous athletes

    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
    uscript
    -0.79
    redients
    -0.77
    worldly
    -0.75
    merce
    -0.74
    shapeshifter
    -0.74
    profits
    -0.73
    perse
    -0.72
    ebin
    -0.72
    tions
    -0.70
    romeda
    -0.69
    POSITIVE LOGITS
     Kardashian
    0.89
     Kennedy
    0.86
     Beckham
    0.84
     Oprah
    0.82
     Frazier
    0.79
     Kardash
    0.79
     Lewis
    0.79
     LeBron
    0.78
     Cruise
    0.77
     Mayweather
    0.76
    Activations Density 0.254%

    No Known Activations