Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20073
    Prev
    Next
    INDEX
    Explanations

    language related to governmental levels, particularly focusing on state and local levels

    oai_token-act-pair · gpt-3.5-turbo

    references to local government entities and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -1.20
    uberty
    -0.92
    vous
    -0.90
    issance
    -0.90
    orst
    -0.89
    gger
    -0.89
    enment
    -0.88
    ACTED
    -0.87
    qq
    -0.85
    lihood
    -0.84
    POSITIVE LOGITS
     jurisdictions
    1.09
     NAACP
    0.95
     ordinances
    0.94
     governments
    0.92
     municipalities
    0.90
     mayors
    0.90
     organizing
    0.90
    ities
    0.88
     organizations
    0.87
     nonprofits
    0.86
    Activations Density 0.043%

    No Known Activations