© 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. 0-RES-JB
    11. 11723
    Prev
    Next
    INDEX
    Explanations

    action verbs related to making sure rules or orders are followed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enforce."

    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
     Went
    -0.67
     Fever
    -0.65
    LV
    -0.63
     Memories
    -0.63
     Dreams
    -0.63
     Surgery
    -0.62
     Ascension
    -0.61
     card
    -0.60
     Pic
    -0.60
    card
    -0.60
    POSITIVE LOGITS
     enforce
    3.67
     enforcing
    2.31
     enforced
    2.05
     enforcement
    1.78
    enforcement
    1.38
     prosecute
    1.31
     Enforcement
    1.31
     obey
    1.24
     impose
    1.23
     implement
    1.19
    Activations Density 0.010%

    No Known Activations