© 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. 7-RES-JB
    11. 15913
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to rules or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experien
    -0.80
    issance
    -0.79
    ONSORED
    -0.79
    ience
    -0.78
     Siem
    -0.70
    ienced
    -0.70
     Hots
    -0.69
    riel
    -0.68
    itate
    -0.67
     Bras
    -0.67
    POSITIVE LOGITS
     governing
    1.10
    breakers
    1.03
    book
    1.00
    books
    0.94
     Enforcement
    0.92
    breaker
    0.91
     violations
    0.90
     lawy
    0.90
     prohibiting
    0.89
     regulating
    0.87
    Activations Density 0.038%

    No Known Activations