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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 19893
    Prev
    Next
    INDEX
    Explanations

    links and buttons for social networking sites

    oai_token-act-pair · gpt-3.5-turbo

    social media engagement metrics

    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
    •Partition Features Layer 8 GPT2 Small
    " token" vs "Token"

    No Comments

    Negative Logits
     brid
    -0.82
     spir
    -0.80
     bending
    -0.78
     choking
    -0.78
     labor
    -0.76
     carving
    -0.76
     increasingly
    -0.75
     ranged
    -0.75
     cens
    -0.74
     pal
    -0.74
    POSITIVE LOGITS
    Advertisements
    1.64
    Conclusion
    1.50
    References
    1.36
    Discussion
    1.30
    Contact
    1.29
    Sources
    1.28
    Send
    1.28
    Loading
    1.27
    Trivia
    1.25
    Official
    1.24
    Activations Density 0.479%

    No Known Activations