© 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. 11-RES-JB
    11. 1428
    Prev
    Next
    INDEX
    Explanations

    language related to legal matters and processes, especially terms related to formal claims and requests

    oai_token-act-pair · gpt-3.5-turbo

    legal and political terminology related to claims and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    byter
    -0.69
    ategory
    -0.64
    ienced
    -0.64
    Spawn
    -0.63
    ensor
    -0.61
     oneself
    -0.59
    ccording
    -0.56
    ritten
    -0.55
    glomer
    -0.54
     Breed
    -0.52
    POSITIVE LOGITS
    ings
    0.83
    naires
    0.82
    nings
    0.76
    breaking
    0.72
    als
    0.71
    ysis
    0.71
    alysis
    0.70
    mates
    0.70
     spree
    0.69
    ãĤ´ãĥ³
    0.69
    Activations Density 0.324%

    No Known Activations