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. 0-RES-JB
    6. 10762
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating a high degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "quite" and its various contexts in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.67
     Each
    -0.60
    stakes
    -0.60
    org
    -0.60
    isin
    -0.60
    inn
    -0.59
    ovo
    -0.58
    adin
    -0.57
     Information
    -0.57
    eded
    -0.55
    POSITIVE LOGITS
     quite
    3.13
    quite
    2.34
    Quite
    1.94
     Quite
    1.85
     pretty
    1.61
     fairly
    1.57
     very
    1.52
     awfully
    1.45
     terribly
    1.43
     somewhat
    1.42
    Activations Density 0.020%

    No Known Activations