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. 9-RES-JB
    6. 20494
    Prev
    Next
    INDEX
    Explanations

    City Council related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to city council members and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.82
     Typh
    -0.75
    ãĥ¼ãĥĨ
    -0.68
     Jihad
    -0.66
     global
    -0.65
     Rowling
    -0.65
     Valiant
    -0.65
     Nietzsche
    -0.64
     mysql
    -0.64
     Abu
    -0.63
    POSITIVE LOGITS
     Commissioners
    1.01
     unanimously
    1.01
    woman
    1.01
    member
    1.01
     adjourn
    0.96
     chambers
    0.93
    Council
    0.92
     district
    0.88
     subcommittee
    0.87
    District
    0.87
    Activations Density 0.139%

    No Known Activations