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. 0-RES-JB
    6. 4626
    Prev
    Next
    INDEX
    Explanations

    single character repeated multiple times in sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or symbol often associated with academic or serious contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cas
    -0.78
     Ca
    -0.73
     cruise
    -0.68
     cran
    -0.67
     mars
    -0.64
     Pers
    -0.64
     bru
    -0.62
     mix
    -0.61
     Tru
    -0.60
     Pon
    -0.60
    POSITIVE LOGITS
    Ł
    4.50
    Ŀ
    1.89
    ¿
    1.82
    İ
    1.75
    ł
    1.73
    ¯
    1.72
    ŀ
    1.71
    ı
    1.71
    £
    1.68
    ¢
    1.67
    Activations Density 0.004%

    No Known Activations