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. 7-RES-JB
    6. 3309
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "the rule of law."

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases emphasizing the concept of "rule of law."

    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
    iations
    -0.78
    MpServer
    -0.70
    BUR
    -0.65
    ']
    -0.65
    âĹ¼
    -0.65
    wcs
    -0.65
    inarily
    -0.64
    iate
    -0.63
    NetMessage
    -0.63
    phrine
    -0.63
    POSITIVE LOGITS
     Bashar
    0.87
     Allaah
    0.83
     Saud
    0.75
     darkness
    0.72
    igion
    0.70
    esses
    0.69
     Islam
    0.68
     Ernst
    0.67
     vengeance
    0.65
     Mohammad
    0.65
    Activations Density 0.115%

    No Known Activations