© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2477
    Prev
    Next
    INDEX
    Explanations

    references to the IRS, particularly related to officials, actions, and statements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the IRS and related officials or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.91
    axter
    -0.86
    theless
    -0.82
    lain
    -0.82
     Jenner
    -0.79
    isations
    -0.78
    ijk
    -0.77
    izations
    -0.76
    hots
    -0.72
    ifest
    -0.72
    POSITIVE LOGITS
     IRS
    0.88
     Revenue
    0.81
     Publication
    0.79
     scrutiny
    0.78
     Commissioner
    0.78
     Accountability
    0.78
     Oversight
    0.77
     audit
    0.76
     FOIA
    0.76
     Regulations
    0.76
    Activations Density 0.024%

    No Known Activations