© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 955
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cath" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words and references related to the Catholic Church and its figures

    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
    culosis
    -0.71
     Fighters
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
     Generations
    -0.65
    ãĥĪ
    -0.63
     flourish
    -0.63
     Acquisition
    -0.63
     Pitch
    -0.62
    itably
    -0.61
    nesota
    -0.61
    POSITIVE LOGITS
    arine
    1.29
    ulhu
    1.12
    olic
    1.11
    ars
    1.10
    olics
    1.05
    cart
    1.00
    ode
    1.00
    odic
    0.92
    mand
    0.91
    ryn
    0.90
    Activations Density 0.072%

    No Known Activations