© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 15287
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or regulatory terms related to the Federal Communications Commission (FCC)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Communications."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gery
    -0.77
    ilts
    -0.72
    lein
    -0.72
    geries
    -0.70
    private
    -0.69
    apache
    -0.68
    yrim
    -0.68
    iless
    -0.68
    olkien
    -0.67
    ĻĤ
    -0.67
    POSITIVE LOGITS
     Communications
    1.13
     Communication
    1.00
     Telecommunications
    0.99
    nect
    0.97
    communications
    0.94
     Connection
    0.89
     Marketing
    0.86
     Services
    0.86
     Industry
    0.83
     Laboratories
    0.83
    Activations Density 0.007%

    No Known Activations