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. 4634
    Prev
    Next
    INDEX
    Explanations

    mentions of specific government committees or departments, particularly related to military or health services

    oai_token-act-pair · gpt-3.5-turbo

    references to government and health services

    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
    ãĥĥãĤ¯
    -0.79
    iple
    -0.73
    alogue
    -0.73
    ãĤ¨ãĥ«
    -0.68
    phrine
    -0.67
    yond
    -0.65
    ãĥ£
    -0.65
    reads
    -0.65
    dream
    -0.65
    share
    -0.65
    POSITIVE LOGITS
     Agency
    1.12
     Administration
    1.10
     Committee
    1.05
     Commission
    0.93
     Administ
    0.92
     Bureau
    0.91
     Loan
    0.90
    ettlement
    0.84
     Commissioner
    0.84
     Council
    0.84
    Activations Density 0.051%

    No Known Activations