© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1240
    Prev
    Next
    INDEX
    Explanations

    references to laws and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terminology and 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
     pinch
    -0.70
     peripheral
    -0.66
     previews
    -0.63
     flow
    -0.63
    â
    -0.62
    xd
    -0.62
     fuel
    -0.62
     Test
    -0.61
     feeds
    -0.61
     Rabbit
    -0.61
    POSITIVE LOGITS
    law
    4.64
    laws
    3.47
    Law
    2.25
     LAW
    1.90
     Law
    1.82
     law
    1.69
     Lawyers
    1.33
    rule
    1.14
    Legal
    1.13
    criminal
    1.13
    Activations Density 0.011%

    No Known Activations