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. 16802
    Prev
    Next
    INDEX
    Explanations

    news-related phrases about email subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that initiate calls to action or engagement

    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
    hesis
    -0.70
    */
    -0.69
    uctor
    -0.68
    handedly
    -0.67
    fortunately
    -0.65
    âĶ
    -0.65
     embod
    -0.64
     outl
    -0.64
     unsc
    -0.63
    FontSize
    -0.63
    POSITIVE LOGITS
     Middles
    0.91
     Transcript
    0.87
     cele
    0.86
     daily
    0.85
     Liverpool
    0.83
     Aston
    0.82
     Manchester
    0.81
    cloneembedreportprint
    0.81
     rugby
    0.81
     Daily
    0.81
    Activations Density 0.024%

    No Known Activations