© 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. 20929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lawyer"

    oai_token-act-pair · gpt-3.5-turbo

    references to legal professionals or lawyers

    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
    wn
    -0.82
    oppers
    -0.80
    plings
    -0.76
    ween
    -0.73
    ende
    -0.73
    Poll
    -0.65
    asted
    -0.63
    poll
    -0.63
     sacred
    -0.62
    itious
    -0.62
    POSITIVE LOGITS
     lawyer
    1.01
     warr
    0.88
    ertodd
    0.85
     solicitor
    0.85
    suit
    0.83
     lawy
    0.79
     attorney
    0.78
    yers
    0.77
    yer
    0.75
     accountant
    0.75
    Activations Density 0.019%

    No Known Activations