Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 19457
    Prev
    Next
    INDEX
    Explanations

    technical terms related to efficiency and optimization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to efficiency and optimization in processes or systems

    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
    Viol
    -0.75
    wrong
    -0.68
    arling
    -0.68
    ODY
    -0.67
    icipated
    -0.63
    omy
    -0.63
    kar
    -0.62
    ature
    -0.62
     divisive
    -0.61
    evil
    -0.61
    POSITIVE LOGITS
     avoids
    1.27
     eliminates
    1.23
     minimized
    1.17
     seamless
    1.10
     streamlined
    1.09
     minim
    1.07
     ease
    1.07
     efficiently
    1.05
     simplicity
    1.05
     seamlessly
    1.05
    Activations Density 0.588%

    No Known Activations