Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8867
    Prev
    Next
    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and their frequent occurrences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     roar
    -0.74
     affiliate
    -0.73
     fury
    -0.72
     arch
    -0.70
     derby
    -0.69
     metro
    -0.69
     Alger
    -0.68
     march
    -0.68
     posting
    -0.68
     Mehran
    -0.67
    POSITIVE LOGITS
    moderate
    1.35
    significant
    1.32
    extremely
    1.30
    almost
    1.27
    sever
    1.26
    neutral
    1.26
    highly
    1.25
    severe
    1.24
    multiple
    1.24
    pure
    1.22
    Activations Density 0.149%

    No Known Activations