© 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
    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. 15473
    Prev
    Next
    INDEX
    Explanations

    years associated with beauty pageant winners and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or list items

    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
     craz
    -0.66
    ieg
    -0.58
     leveled
    -0.57
     Gins
    -0.55
     gigg
    -0.55
    nox
    -0.53
     Rocks
    -0.53
     Appalach
    -0.53
     horm
    -0.52
     blender
    -0.52
    POSITIVE LOGITS
     âĢ¢
    3.82
    âĢ¢
    2.47
     ·
    2.12
     âĸł
    1.98
     âĹı
    1.81
     âĸº
    1.67
    âĸł
    1.62
    âĢ¢âĢ¢
    1.59
     »
    1.55
    âϦ
    1.47
    Activations Density 0.012%

    No Known Activations