© 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. 1-RES-JB
    11. 11489
    Prev
    Next
    INDEX
    Explanations

    words related to legal processes, specifically the concept of a 'warrant'

    oai_token-act-pair · gpt-3.5-turbo

    references to legal warrants and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hhhh
    -0.69
    hh
    -0.67
     Catch
    -0.64
    este
    -0.64
     Norn
    -0.61
    udd
    -0.61
    ̶
    -0.60
    tax
    -0.59
    ttle
    -0.59
    inks
    -0.58
    POSITIVE LOGITS
     warrants
    1.49
     warrant
    1.47
     warr
    0.94
     Warrant
    0.91
    ably
    0.86
    ments
    0.83
    itures
    0.82
     warranted
    0.82
    MENTS
    0.76
    INGTON
    0.75
    Activations Density 0.010%

    No Known Activations