© 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. 11-RES-JB
    11. 7790
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and legal systems

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to legal concepts and frameworks

    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
    asks
    -0.77
    irs
    -0.70
    pter
    -0.69
     ILCS
    -0.68
    ...]
    -0.68
    idays
    -0.67
    caster
    -0.67
    ega
    -0.67
    ments
    -0.66
    ier
    -0.65
    POSITIVE LOGITS
     thumb
    1.26
     thirds
    0.95
     averages
    0.94
     conduct
    0.84
     engagement
    0.84
     diminishing
    0.82
     physics
    0.82
     Acquisition
    0.81
     unintended
    0.78
     legality
    0.78
    Activations Density 0.070%

    No Known Activations