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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7047
    Prev
    Next
    INDEX
    Explanations

    text formatting characters, specifically a specific character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain numerical values or references to quantified information

    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
     describ
    -0.80
     oun
    -0.75
     exha
    -0.73
     proport
    -0.70
     corrid
    -0.69
     artists
    -0.69
     undermin
    -0.69
     neighb
    -0.68
     tradem
    -0.68
     tremend
    -0.68
    POSITIVE LOGITS
    Republican
    1.04
    TRUMP
    1.04
    GOP
    0.96
    Hillary
    0.95
    Obama
    0.95
    Romney
    0.93
    Clinton
    0.93
    Republicans
    0.92
    Trump
    0.92
    Donald
    0.91
    Activations Density 0.587%

    No Known Activations