© 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. 65
    Prev
    Next
    INDEX
    Explanations

    words related to production or creation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "produce."

    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
    nee
    -0.84
    laus
    -0.83
    phe
    -0.71
    ser
    -0.68
    sie
    -0.68
     Hilbert
    -0.65
    bole
    -0.65
    bi
    -0.64
    uyomi
    -0.64
    ede
    -0.62
    POSITIVE LOGITS
    ivity
    0.99
    女
    0.92
    Output
    0.91
    encers
    0.89
     outputs
    0.84
    furt
    0.83
     output
    0.80
     produce
    0.80
     PRODUCT
    0.79
    ivities
    0.78
    Activations Density 0.024%

    No Known Activations