© 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. 7-RES-JB
    11. 12450
    Prev
    Next
    INDEX
    Explanations

    words related to exemptions or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exemptions and exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¥
    -0.77
    kr
    -0.70
     Xiang
    -0.69
     Zeit
    -0.65
     Roose
    -0.63
    plays
    -0.63
     Io
    -0.62
     Verge
    -0.62
     Toast
    -0.61
     Bras
    -0.61
    POSITIVE LOGITS
     exemptions
    1.13
     exempt
    1.03
     exemption
    1.03
     exempted
    0.93
     immunity
    0.92
    exempt
    0.87
    untarily
    0.80
    emption
    0.79
    icut
    0.78
     afforded
    0.77
    Activations Density 0.033%

    No Known Activations