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. 12-RES-JB
    6. 15140
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, individuals, and organizations, particularly in the context of government and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words or fragments related to the name "Waukesha"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     slam
    -0.64
     crunch
    -0.54
     Chr
    -0.51
     bust
    -0.51
     dread
    -0.51
     distinct
    -0.51
     Crunch
    -0.50
     Sapphire
    -0.50
     soph
    -0.49
     conv
    -0.48
    POSITIVE LOGITS
    ipeg
    1.10
    nesday
    1.10
    atever
    0.94
    hester
    0.89
    ankind
    0.87
    bledon
    0.86
    ÅĤ
    0.84
    itzer
    0.81
    WT
    0.80
    cester
    0.78
    Activations Density 0.169%

    No Known Activations