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. 1422
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives describing size or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concept of size or magnitude, particularly the word "bigger."

    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
    shire
    -0.97
    chron
    -0.79
    AUT
    -0.78
    gemony
    -0.77
     Examiner
    -0.68
    syn
    -0.68
    oire
    -0.68
     Michaels
    -0.68
    endant
    -0.68
     Zimmer
    -0.67
    POSITIVE LOGITS
     eleph
    0.94
     proble
    0.92
     millenn
    0.90
    izont
    0.89
     spons
    0.86
     sized
    0.82
     consequential
    0.81
     boobs
    0.81
     dilig
    0.80
     notor
    0.79
    Activations Density 0.006%

    No Known Activations