© 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. 3882
    Prev
    Next
    INDEX
    Explanations

    specific terms representing legal contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "case" along with its variations, indicating a focus on case studies or examples

    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
    glers
    -0.68
    catentry
    -0.67
    resent
    -0.66
    arus
    -0.64
    rones
    -0.64
    issance
    -0.64
    hered
    -0.63
    oves
    -0.62
    onder
    -0.62
    orks
    -0.62
    POSITIVE LOGITS
     study
    0.98
     Study
    0.85
     insensitive
    0.82
     histories
    0.82
     studies
    0.81
     scenario
    0.78
     STUD
    0.77
     Keen
    0.76
    cmp
    0.74
     Studies
    0.73
    Activations Density 0.042%

    No Known Activations