Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23494
    Prev
    Next
    INDEX
    Explanations

    facts and information related to famous historical figures, specifically in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to historical political events and figures related to Cuba

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     EPS
    -1.03
    NVIDIA
    -0.83
     Gears
    -0.81
     Subaru
    -0.79
    aukee
    -0.78
     Fenrir
    -0.78
     Horses
    -0.78
    Gamer
    -0.78
     horse
    -0.78
     eSports
    -0.76
    POSITIVE LOGITS
     Cuban
    2.69
     Havana
    2.63
     Cuba
    2.62
     Castro
    2.34
    Cub
    2.29
     Fidel
    2.16
     Cub
    2.12
     Nicarag
    1.70
     Nicaragua
    1.62
     Dominican
    1.60
    Activations Density 0.116%

    No Known Activations