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. 8-RES-JB
    6. 21793
    Prev
    Next
    INDEX
    Explanations

    keywords related to fandom and specific interests or preferences, such as being a fan of a particular brand or a type of media

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply a direct address to the reader or audience

    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
    minster
    -0.65
    osite
    -0.61
    ELD
    -0.61
    Whe
    -0.60
    Brand
    -0.59
    OGR
    -0.59
    ener
    -0.58
    ¬¼
    -0.57
    ogenesis
    -0.57
    ThumbnailImage
    -0.56
    POSITIVE LOGITS
     congratulations
    1.23
     chances
    1.08
     congr
    1.07
     please
    1.00
    please
    0.91
     beware
    0.89
     PLEASE
    0.85
    pmwiki
    0.83
    you
    0.78
    then
    0.78
    Activations Density 0.213%

    No Known Activations