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. 17071
    Prev
    Next
    INDEX
    Explanations

    references to governing bodies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "council."

    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
     âī
    -0.75
    Ô
    -0.69
    Vert
    -0.68
    ®
    -0.65
     Surprise
    -0.63
     MV
    -0.62
     vertically
    -0.62
    Ns
    -0.61
     VIDEOS
    -0.61
    olor
    -0.61
    POSITIVE LOGITS
     council
    3.71
    Council
    2.98
     councils
    2.85
     Council
    2.70
     councillors
    2.46
     councillor
    2.20
    Coun
    1.67
     Coun
    1.61
     mayor
    1.52
     mayoral
    1.50
    Activations Density 0.013%

    No Known Activations