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. 7-RES-JB
    6. 10790
    Prev
    Next
    INDEX
    Explanations

    terms related to political bases and demographics

    oai_token-act-pair · gpt-3.5-turbo

    references to different voter bases and their political affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.78
     protocol
    -0.73
     Protocol
    -0.66
    orius
    -0.64
     Nanto
    -0.64
     tread
    -0.64
     bye
    -0.63
    planet
    -0.63
    saf
    -0.62
     timestamp
    -0.62
    POSITIVE LOGITS
     disillusion
    1.09
     electorate
    1.04
     voters
    1.02
     demographics
    1.00
     evangelicals
    0.96
     alienated
    0.95
     demographic
    0.95
    enfranch
    0.92
     millennials
    0.91
     constituencies
    0.90
    Activations Density 0.307%

    No Known Activations