© 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. 10-RES-JB
    11. 2315
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex legal, technical, and practical issues, including navigation and paperwork

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and bureaucratic challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Positive
    -0.77
    Cola
    -0.75
    Naz
    -0.73
     Enhancement
    -0.71
    Favorite
    -0.71
    waukee
    -0.71
    arers
    -0.70
    shown
    -0.70
    reciation
    -0.69
    nor
    -0.68
    POSITIVE LOGITS
     complexities
    1.53
     tangled
    1.45
     intric
    1.44
     convoluted
    1.37
     complicated
    1.35
     bureaucracy
    1.35
     maze
    1.33
     bureaucratic
    1.26
     labyrinth
    1.26
     nuances
    1.25
    Activations Density 0.417%

    No Known Activations