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. 19368
    Prev
    Next
    INDEX
    Explanations

    keywords related to the Internal Revenue Service (IRS), particularly focusing on mentions of specific IRS officials and operations

    oai_token-act-pair · gpt-3.5-turbo

    references to the IRS and its officials

    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
    boards
    -0.94
    theless
    -0.82
    hots
    -0.80
    axter
    -0.79
    lain
    -0.78
    isations
    -0.77
    izations
    -0.75
    board
    -0.74
    ifest
    -0.74
    ijk
    -0.71
    POSITIVE LOGITS
     IRS
    0.90
     Accountability
    0.78
     Oversight
    0.77
     levied
    0.75
     scrutiny
    0.74
    eteria
    0.73
     Revenue
    0.72
     Commissioner
    0.72
     sting
    0.72
     bureaucracy
    0.72
    Activations Density 0.027%

    No Known Activations