© 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. 8-RES-JB
    11. 18673
    Prev
    Next
    INDEX
    Explanations

    specific terms related to the circus arts, particularly related to "Cirque du Soleil"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rights and regulations associated with a specific group or entity

    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
     McCl
    -0.76
    ãĥ£
    -0.75
     Git
    -0.71
     Bers
    -0.70
     Bei
    -0.69
     digitally
    -0.68
     CJ
    -0.67
     CS
    -0.66
    chnology
    -0.66
     Gavin
    -0.66
    POSITIVE LOGITS
    olding
    0.89
    fort
    0.88
    OLD
    0.85
     Lodge
    0.84
     Rowe
    0.80
    rief
    0.77
    oard
    0.77
    nob
    0.76
    icent
    0.76
    olded
    0.76
    Activations Density 0.271%

    No Known Activations