© 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. 11-RES-JB
    11. 7694
    Prev
    Next
    INDEX
    Explanations

    special characters amidst text

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain numerical data or statistics

    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
     scrambling
    -0.73
     occas
    -0.71
     footing
    -0.67
     helicop
    -0.66
     proport
    -0.66
     hindsight
    -0.65
     undermin
    -0.65
     unprepared
    -0.64
     tink
    -0.64
     sucker
    -0.64
    POSITIVE LOGITS
    DragonMagazine
    1.00
    Ú
    0.91
    à¦
    0.89
    Lenin
    0.88
    Balt
    0.88
    Moreover
    0.88
    Ku
    0.87
    âĵĺ
    0.87
    nai
    0.85
    ³³³³³³³³³³³³³³³³
    0.85
    Activations Density 0.469%

    No Known Activations