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. 6752
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of sentences, particularly those relating to political topics

    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
     glim
    -0.85
     uncommon
    -0.78
     healer
    -0.78
     handmade
    -0.78
     helper
    -0.77
     workspace
    -0.77
     challeng
    -0.76
     hatch
    -0.76
     quir
    -0.75
     disemb
    -0.75
    POSITIVE LOGITS
     Worse
    1.48
     Meanwhile
    1.35
     Ironically
    1.30
     Needless
    1.28
     Thus
    1.21
     Moreover
    1.20
     Apparently
    1.20
     Hence
    1.18
     Surely
    1.15
     Shame
    1.15
    Activations Density 0.513%

    No Known Activations