© 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. 0-RES-JB
    11. 14668
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or laws, particularly related to constitutions

    oai_token-act-pair · gpt-3.5-turbo

    references to constitutions or constitutional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    done
    -0.74
    ay
    -0.68
     Done
    -0.67
    Tip
    -0.66
     Lur
    -0.66
     racks
    -0.63
     Lane
    -0.62
     Hai
    -0.62
     crews
    -0.61
     Wor
    -0.61
    POSITIVE LOGITS
     constitution
    3.92
     Constitution
    2.46
     constitutional
    1.64
     constitu
    1.55
    Const
    1.48
     constit
    1.41
     Constitutional
    1.37
     legality
    1.20
    constitutional
    1.18
     legislature
    1.15
    Activations Density 0.014%

    No Known Activations