© 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. 2-RES-JB
    11. 12698
    Prev
    Next
    INDEX
    Explanations

    references to dining locations or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to dining and seating arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archangel
    -0.77
     Aerospace
    -0.75
     Watts
    -0.69
     Mub
    -0.69
    vernment
    -0.68
     PAT
    -0.68
    RAY
    -0.67
     Mehran
    -0.67
    Downloadha
    -0.65
     Kinnikuman
    -0.64
    POSITIVE LOGITS
     dining
    1.08
     halls
    0.99
     Restaur
    0.96
    eteria
    0.94
     establishments
    0.89
     tastes
    0.89
     restaurants
    0.88
    iasco
    0.88
    stairs
    0.85
     meals
    0.84
    Activations Density 0.014%

    No Known Activations