© 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. 23995
    Prev
    Next
    INDEX
    Explanations

    text related to legal and constitutional rights

    oai_token-act-pair · gpt-3.5-turbo

    references to fundamental rights and legal principles

    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
     outage
    -0.85
    glers
    -0.82
     Canaver
    -0.75
     SLI
    -0.74
    Arcade
    -0.72
    cigarettes
    -0.67
     blamed
    -0.67
    mouth
    -0.66
     blitz
    -0.66
     migraine
    -0.66
    POSITIVE LOGITS
     Declaration
    1.42
     Constitution
    1.41
     bedrock
    1.21
     constitution
    1.20
     Founders
    1.17
     founding
    1.14
     Founding
    1.14
     oath
    1.12
     dignity
    1.12
     freedoms
    1.10
    Activations Density 0.317%

    No Known Activations