© 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. 18753
    Prev
    Next
    INDEX
    Explanations

    legal terms and legislation-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official declarations or legal language

    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
     fooled
    -0.79
     gigs
    -0.68
    iltr
    -0.68
    iddled
    -0.67
    ammed
    -0.65
    steel
    -0.64
    itbart
    -0.64
    ospace
    -0.64
    ampire
    -0.62
     tricked
    -0.62
    POSITIVE LOGITS
     hereby
    1.49
     shall
    1.28
    shall
    1.24
     appoint
    1.14
     promul
    1.13
     authorize
    1.13
     pursuant
    1.08
     delegated
    1.07
     certify
    1.06
     thereof
    1.04
    Activations Density 0.298%

    No Known Activations