© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19647
    Prev
    Next
    INDEX
    Explanations

    words related to legal professions, especially the term "attorney."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal representation and attorneys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plings
    -0.71
     Railway
    -0.69
    wn
    -0.68
    auri
    -0.68
    mitt
    -0.67
    odus
    -0.61
    ween
    -0.61
    obyl
    -0.59
    lihood
    -0.59
     Main
    -0.59
    POSITIVE LOGITS
     attorney
    0.95
     warr
    0.89
    rored
    0.82
     solicitor
    0.80
    orneys
    0.79
    alty
    0.78
    alties
    0.73
     examiner
    0.73
    general
    0.73
     lawyer
    0.72
    Activations Density 0.018%

    No Known Activations