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. 10-RES-JB
    6. 21231
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and storytelling

    oai_token-act-pair · gpt-3.5-turbo

    instances of communication and instructions given to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.69
     contemporaries
    -0.65
     rhet
    -0.65
    ¿½
    -0.64
    aic
    -0.64
    £ı
    -0.63
    Thumbnail
    -0.62
     Economist
    -0.61
     concerted
    -0.61
    egal
    -0.60
    POSITIVE LOGITS
     shouldn
    1.08
     should
    0.94
     ought
    0.93
     smelled
    0.90
     alright
    0.89
     okay
    0.86
    should
    0.85
     couldn
    0.85
     needed
    0.82
    'll
    0.79
    Activations Density 0.305%

    No Known Activations