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

    Neuronpedia

    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. 10-RES-JB
    11. 18629
    Prev
    Next
    INDEX
    Explanations

    keywords related to prosthetics and puppets

    oai_token-act-pair · gpt-3.5-turbo

    words related to puppetry and prosthetics

    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
    ting
    -0.74
    ivities
    -0.67
    fully
    -0.64
    ARB
    -0.63
    med
    -0.62
    utory
    -0.62
    ript
    -0.61
     Lith
    -0.61
    ãĥĥãĤ¯
    -0.61
    arta
    -0.60
    POSITIVE LOGITS
    etry
    1.11
    ete
    0.99
    uppet
    0.84
    elines
    0.84
     pupp
    0.81
    hett
    0.81
    sburgh
    0.80
    ignt
    0.79
    hetics
    0.78
    eworks
    0.77
    Activations Density 0.076%

    No Known Activations