© 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. 11-RES-JB
    11. 9289
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts or laws

    oai_token-act-pair · gpt-3.5-turbo

    statements related to the legality of actions and the consequences under law

    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
    itiveness
    -0.81
    ãĤ©
    -0.72
    builders
    -0.69
     Watt
    -0.68
     Horizons
    -0.66
    ffe
    -0.66
     helm
    -0.65
    backer
    -0.65
     Hast
    -0.65
    nerg
    -0.65
    POSITIVE LOGITS
     punishable
    1.76
     illegal
    1.68
     permissible
    1.61
     prohibited
    1.58
     forbidden
    1.56
     unlawful
    1.51
     outlawed
    1.46
    illegal
    1.43
     lawful
    1.43
     unconstitutional
    1.42
    Activations Density 0.284%

    No Known Activations