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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14732
    Prev
    Next
    INDEX
    Explanations

    topics or subjects with the word "Rules" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rules" or "Rule" in various contexts

    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
     tracking
    -0.68
     carry
    -0.68
     dist
    -0.67
    ioch
    -0.67
     output
    -0.66
     track
    -0.65
     centre
    -0.64
     mass
    -0.64
     department
    -0.64
    hd
    -0.63
    POSITIVE LOGITS
     Rules
    3.37
     Rule
    2.89
    Rules
    2.28
    Rule
    2.19
    rules
    1.66
     Clause
    1.24
     Procedures
    1.22
     Laws
    1.21
     Procedure
    1.18
     Principles
    1.18
    Activations Density 0.029%

    No Known Activations