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. 10-RES-JB
    6. 13115
    Prev
    Next
    INDEX
    Explanations

    words related to royalty, kings, and kingdoms

    oai_token-act-pair · gpt-3.5-turbo

    words related to royalty and monarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exposure
    -0.83
     Investigations
    -0.81
     Reports
    -0.77
    Journal
    -0.76
     Reviews
    -0.76
     Indie
    -0.76
     Strip
    -0.75
     Exper
    -0.74
     Laboratory
    -0.74
     Solutions
    -0.74
    POSITIVE LOGITS
    esses
    1.36
    pin
    1.23
    pins
    1.16
     prince
    1.15
     decree
    1.14
     princes
    1.14
    doms
    1.06
    ess
    1.03
    dom
    1.02
    lord
    1.02
    Activations Density 0.082%

    No Known Activations