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. 0-RES-JB
    6. 22810
    Prev
    Next
    INDEX
    Explanations

    political and economic terms

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to political and governmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     range
    -0.90
     arch
    -0.88
     P
    -0.86
     bi
    -0.84
     M
    -0.84
     B
    -0.83
     Y
    -0.83
     host
    -0.82
     exit
    -0.82
     co
    -0.82
    POSITIVE LOGITS
    Political
    1.94
    Economic
    1.77
    Engineers
    1.73
    Sexual
    1.72
    Democrats
    1.67
    Government
    1.66
    Climate
    1.66
    Council
    1.65
    Republicans
    1.65
    Scientists
    1.65
    Activations Density 0.161%

    No Known Activations