© 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. 20538
    Prev
    Next
    INDEX
    Explanations

    descriptions of legal or official processes and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and judicial processes

    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
    ieu
    -0.66
    onics
    -0.65
    ocation
    -0.64
    iasm
    -0.62
    earchers
    -0.62
     Goodbye
    -0.60
     Disapp
    -0.60
    rift
    -0.60
    hens
    -0.59
    tek
    -0.58
    POSITIVE LOGITS
     already
    1.24
     expressly
    1.00
     otherwise
    0.94
     arguably
    0.93
     clearly
    0.93
     supposedly
    0.91
     explicitly
    0.90
     previously
    0.90
     undeniably
    0.89
     notoriously
    0.88
    Activations Density 0.672%

    No Known Activations