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

    Neuronpedia

    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. 4-RES-JB
    11. 17155
    Prev
    Next
    INDEX
    Explanations

    acronyms related to regulatory agencies, specifically the FCC

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the FCC, a regulatory body

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

    No Comments

    Negative Logits
     Kubrick
    -0.76
    estate
    -0.71
    ku
    -0.69
    onyms
    -0.69
    Tu
    -0.68
     Pers
    -0.65
    cock
    -0.65
    minster
    -0.64
    itarian
    -0.63
     Celtic
    -0.62
    POSITIVE LOGITS
     Commissioners
    1.07
     commissioners
    1.06
     Commissioner
    0.97
     commissioner
    0.95
     filings
    0.83
     FCC
    0.82
     Commission
    0.80
    CCC
    0.78
     regulates
    0.78
    nect
    0.76
    Activations Density 0.010%

    No Known Activations