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. 22098
    Prev
    Next
    INDEX
    Explanations

    political party abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political parties or groups

    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
    world
    -0.68
     airplanes
    -0.66
     traveling
    -0.64
     liv
    -0.64
    Dom
    -0.64
     Bod
    -0.63
    mares
    -0.63
     Benson
    -0.62
    whe
    -0.62
     apparel
    -0.61
    POSITIVE LOGITS
     SNP
    3.90
     UKIP
    1.82
     DUP
    1.74
     Ukip
    1.63
     Sturgeon
    1.56
     Tories
    1.53
     allele
    1.35
     ANC
    1.32
     Scottish
    1.31
     Tory
    1.31
    Activations Density 0.021%

    No Known Activations