© 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. 3-RES-JB
    11. 20520
    Prev
    Next
    INDEX
    Explanations

    names related to the surnames "Shaw" and "Vaughan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on characters or people named "Shaw," "Haw," "Barber," or "Vaughan."

    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
    Nap
    -0.76
     Roose
    -0.70
     ré
    -0.68
    olith
    -0.67
    cius
    -0.67
    ppings
    -0.66
     kindred
    -0.65
     ven
    -0.63
     Reincarn
    -0.62
     Priv
    -0.62
    POSITIVE LOGITS
    haw
    0.94
    aii
    0.91
    boxing
    0.82
    intosh
    0.81
    mallow
    0.78
    inson
    0.77
     fixme
    0.75
    daq
    0.74
    uckle
    0.73
    cling
    0.73
    Activations Density 0.016%

    No Known Activations