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. 1-RES-JB
    6. 6165
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "static," such as "static electricity" and "static pages."

    oai_token-act-pair · gpt-3.5-turbo

    references to static concepts or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vest
    -0.93
    ishops
    -0.83
    orney
    -0.82
    ongs
    -0.78
    orie
    -0.78
    arenthood
    -0.77
    gans
    -0.75
    ingo
    -0.75
    ñ
    -0.74
    amins
    -0.74
    POSITIVE LOGITS
     static
    1.05
    static
    0.81
     reactive
    0.78
     inline
    0.76
     electricity
    0.74
     upkeep
    0.74
    animate
    0.71
     Static
    0.70
     wallpaper
    0.69
     recoil
    0.69
    Activations Density 0.004%

    No Known Activations