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. 11-RES-JB
    6. 7353
    Prev
    Next
    INDEX
    Explanations

    mentions of political constituencies

    oai_token-act-pair · gpt-3.5-turbo

    references to political constituencies and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usat
    -0.79
    NBA
    -0.74
    Reviewer
    -0.74
    hedon
    -0.74
    NFL
    -0.71
     airplanes
    -0.69
    Copyright
    -0.68
    Autom
    -0.68
    itized
    -0.68
    ASHINGTON
    -0.68
    POSITIVE LOGITS
     constituency
    1.58
     councillor
    1.47
     UKIP
    1.45
     Ukip
    1.36
     MLA
    1.33
     Labour
    1.33
     MP
    1.31
     Liberal
    1.31
     SNP
    1.28
     councillors
    1.27
    Activations Density 0.339%

    No Known Activations