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. 6-RES-JB
    6. 16313
    Prev
    Next
    INDEX
    Explanations

    references to political parties, organizations, and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.80
    ritch
    -0.80
    ickets
    -0.80
     Kathryn
    -0.78
    holes
    -0.74
    Jones
    -0.73
    thy
    -0.71
    ttes
    -0.70
    Jenn
    -0.70
     trout
    -0.69
    POSITIVE LOGITS
     Organisation
    1.07
     Directorate
    1.00
     Organization
    0.93
     Programme
    0.91
     Liberation
    0.89
     Yuan
    0.88
     Assembly
    0.87
     Struggle
    0.87
    fecture
    0.84
     Defence
    0.82
    Activations Density 0.193%

    No Known Activations