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. 6-RES-JB
    6. 4724
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring safety, compliance, and well-being

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of assurance or guarantee

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.76
    itting
    -0.67
     cents
    -0.66
    PsyNetMessage
    -0.66
    court
    -0.64
    kers
    -0.64
     Nanto
    -0.64
    æ©
    -0.62
    Rated
    -0.62
    question
    -0.61
    POSITIVE LOGITS
    ially
    0.88
     adequate
    0.75
     Ensure
    0.73
     sustainability
    0.70
     sust
    0.70
     compliance
    0.70
    lessly
    0.70
     preservation
    0.70
     Lauder
    0.69
     fulfil
    0.69
    Activations Density 0.032%

    No Known Activations