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

    Neuronpedia

    Jacobian LensNEW
    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. 5900
    Prev
    Next
    INDEX
    Explanations

    French words with accents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "Ļ"

    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
     yield
    -0.79
     chained
    -0.75
     fructose
    -0.75
     diving
    -0.74
     recycling
    -0.73
     weave
    -0.73
     selling
    -0.73
     Pyramid
    -0.71
     listing
    -0.70
     partnerships
    -0.70
    POSITIVE LOGITS
    ï¸ı
    1.46
    20439
    1.18
    Balt
    1.15
    vernment
    1.11
    esc
    1.08
    nai
    1.08
    女
    1.08
    ember
    1.07
    £
    1.07
    âĸł
    1.05
    Activations Density 0.190%

    No Known Activations