© 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. 3-RES-JB
    11. 704
    Prev
    Next
    INDEX
    Explanations

    mentions of legal professionals such as lawyers

    oai_token-act-pair · gpt-3.5-turbo

    references to legal professionals and their role in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.80
     Railroad
    -0.70
    ctr
    -0.68
     Railway
    -0.68
     Reincarn
    -0.64
    ween
    -0.62
    plings
    -0.62
    Tro
    -0.62
    Poll
    -0.62
     Bengal
    -0.61
    POSITIVE LOGITS
     warr
    0.93
    ynt
    0.86
    suits
    0.83
    suit
    0.82
    yers
    0.82
     lawy
    0.81
    yer
    0.80
    maid
    0.78
     examiner
    0.76
     specializing
    0.74
    Activations Density 0.018%

    No Known Activations