© 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. 3077
    Prev
    Next
    INDEX
    Explanations

    formal language or procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "formal" or related contexts referring to official procedures and requests

    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
     Tycoon
    -0.91
    ONES
    -0.72
     Tsukuyomi
    -0.68
     Revis
    -0.67
     wisely
    -0.66
     mosquitoes
    -0.62
    Phones
    -0.62
     Stanton
    -0.62
    Rogue
    -0.62
     beware
    -0.61
    POSITIVE LOGITS
    ities
    1.46
    ized
    1.30
    ised
    1.18
    izing
    1.15
    ization
    1.08
    izations
    1.08
    isations
    1.07
    ising
    1.04
    ize
    1.02
    izes
    1.02
    Activations Density 0.037%

    No Known Activations