© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17651
    Prev
    Next
    INDEX
    Explanations

    mentions of political actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    specific political actions or decisions and their implications

    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
    !/
    -0.62
     beautifully
    -0.59
    fortunately
    -0.58
     wonderfully
    -0.57
     lovely
    -0.55
    tumblr
    -0.55
     fascinating
    -0.55
     thrill
    -0.55
     fortunately
    -0.54
    etimes
    -0.54
    POSITIVE LOGITS
    license
    0.76
     unilaterally
    0.65
    ISA
    0.61
     pending
    0.60
     legally
    0.59
     footing
    0.58
     complying
    0.58
     regulations
    0.57
     unconstitutional
    0.57
     funding
    0.57
    Activations Density 1.074%

    No Known Activations