© 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. 0-RES-JB
    11. 16672
    Prev
    Next
    INDEX
    Explanations

    mentions of the technology "WebGL"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "WebGL" technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vie
    -0.69
     tom
    -0.68
     Mish
    -0.66
     Chiefs
    -0.66
     burial
    -0.66
     Ware
    -0.65
     techno
    -0.65
     techn
    -0.64
     circum
    -0.64
     Jed
    -0.62
    POSITIVE LOGITS
    GL
    4.28
     GL
    2.18
    gl
    1.87
    Gl
    1.62
    GS
    1.51
    GF
    1.42
    GR
    1.37
    GH
    1.33
    GT
    1.33
    GN
    1.29
    Activations Density 0.023%

    No Known Activations