© 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. 5614
    Prev
    Next
    INDEX
    Explanations

    specific names and titles

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to academic and creative figures

    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
    eper
    -0.84
    lectic
    -0.73
    igree
    -0.73
    oppers
    -0.73
    atile
    -0.73
    ĸļ
    -0.72
    pora
    -0.72
    atcher
    -0.71
    rary
    -0.71
    eatures
    -0.70
    POSITIVE LOGITS
    brush
    0.86
     Bard
    0.85
     grou
    0.79
     sage
    0.78
     Shant
    0.72
     spirits
    0.71
    NES
    0.71
    aign
    0.70
    bard
    0.69
    stown
    0.69
    Activations Density 0.014%

    No Known Activations