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. 18105
    Prev
    Next
    INDEX
    Explanations

    words related to electrical grids

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a "grid."

    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
    iasis
    -0.79
    doms
    -0.74
    /+
    -0.71
    ————————
    -0.70
    ermott
    -0.70
     Norn
    -0.70
    ership
    -0.69
    0000
    -0.68
     Tob
    -0.67
    ---------------
    -0.66
    POSITIVE LOGITS
     grid
    1.45
     grids
    1.29
     Grid
    0.99
    grid
    0.91
     layout
    0.87
    iron
    0.86
     showc
    0.80
     connectivity
    0.79
    izoph
    0.78
     layouts
    0.78
    Activations Density 0.008%

    No Known Activations