Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15112
    Prev
    Next
    INDEX
    Explanations

    names of legal professionals

    oai_token-act-pair · gpt-3.5-turbo

    names of judges and justices in legal contexts

    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
    ontent
    -0.76
     [|
    -0.72
     borrowed
    -0.67
     cov
    -0.65
     wors
    -0.63
     linem
    -0.63
     rescuing
    -0.63
     stub
    -0.61
     toget
    -0.60
    accompan
    -0.60
    POSITIVE LOGITS
     Judge
    1.13
    Judge
    1.02
     Appeals
    0.98
     Scalia
    0.94
     Circuit
    0.92
     Jury
    0.90
     Justice
    0.87
     Gorsuch
    0.86
    istrate
    0.84
     Trial
    0.83
    Activations Density 0.068%

    No Known Activations