© 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. 2844
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to performance metrics in technology and products

    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
    ril
    -0.75
    IRC
    -0.72
    ovie
    -0.71
     Penal
    -0.69
     PUBLIC
    -0.69
     Franch
    -0.68
     Ending
    -0.66
     disbanded
    -0.64
    ogie
    -0.63
    ANN
    -0.62
    POSITIVE LOGITS
     capabilities
    1.10
     advantages
    1.10
     efficiency
    1.09
     enhancements
    1.03
     capability
    1.01
     superiority
    1.01
     gains
    1.01
     optimizations
    1.01
     improvements
    0.98
     throughput
    0.97
    Activations Density 0.167%

    No Known Activations