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. 3107
    Prev
    Next
    INDEX
    Explanations

    words related to legal and governmental issues, especially related to laws, amendments, and proposals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government policies and legislative actions

    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
     Hawai
    -0.82
     counselor
    -0.81
    sburgh
    -0.79
     Akron
    -0.77
    Miami
    -0.75
     Fargo
    -0.74
     Cind
    -0.73
     Midwest
    -0.73
    é¾įåĸļ士
    -0.73
     Charleston
    -0.72
    POSITIVE LOGITS
     amendments
    1.36
     parliament
    1.30
     MPs
    1.30
     legisl
    1.24
     Parliament
    1.23
     legislation
    1.22
     parliamentary
    1.22
    liament
    1.14
    Labour
    1.14
     Parliamentary
    1.13
    Activations Density 0.422%

    No Known Activations