© 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. 2-RES-JB
    11. 23684
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal matters, such as "legal representation" and "immigration courts"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal concepts or representation

    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
     metic
    -0.70
    naires
    -0.68
     revolves
    -0.67
    caps
    -0.65
     proble
    -0.65
     destro
    -0.63
     Mamm
    -0.63
     undet
    -0.63
    toe
    -0.63
     awa
    -0.63
    POSITIVE LOGITS
    tein
    0.74
    ucky
    0.67
    ripp
    0.64
     Gravity
    0.64
    oday
    0.64
    emade
    0.64
     Roses
    0.64
    rition
    0.64
    abet
    0.63
     Verge
    0.62
    Activations Density 0.000%

    No Known Activations