Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10812
    Prev
    Next
    INDEX
    Explanations

    phrases related to violation of rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating violations of laws or regulations

    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
    GROUND
    -0.63
    idays
    -0.62
     orally
    -0.61
    iances
    -0.57
     Illum
    -0.56
    Finish
    -0.55
     awoken
    -0.54
     succeed
    -0.53
     overcame
    -0.53
     intending
    -0.52
    POSITIVE LOGITS
    escap
    1.26
    humane
    1.23
    essential
    1.07
    offensive
    1.06
    authent
    1.04
     jeopardy
    1.04
     contradiction
    1.03
    arg
    1.01
    ext
    0.99
     fact
    0.97
    Activations Density 0.102%

    No Known Activations