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. 6-RES-JB
    6. 21530
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking a stand or standing up for something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "stand" in various contexts of assertion and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.72
    EStreamFrame
    -0.70
    ilers
    -0.69
    ilic
    -0.69
    ilk
    -0.65
    illian
    -0.64
    iling
    -0.64
    nesota
    -0.62
    hy
    -0.61
    metry
    -0.61
    POSITIVE LOGITS
    still
    1.22
     tall
    0.88
     vigil
    0.80
     desks
    0.78
     upright
    0.76
    anke
    0.75
     steadfast
    0.72
     taller
    0.72
     up
    0.72
    outs
    0.71
    Activations Density 0.027%

    No Known Activations