© 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. 8-RES-JB
    11. 4302
    Prev
    Next
    INDEX
    Explanations

    terms related to software or technology features and commands

    oai_token-act-pair · gpt-3.5-turbo

    product names and services related to technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slaughtered
    -0.75
     surn
    -0.74
     proclamation
    -0.74
     refrain
    -0.73
     wast
    -0.72
    ³³³³³³³³³³³³³³³³
    -0.72
     marching
    -0.71
     spoken
    -0.71
     repealing
    -0.71
     pressed
    -0.70
    POSITIVE LOGITS
    Tools
    1.31
    Plugin
    1.18
    Tool
    1.15
    tools
    1.05
    Widget
    1.03
    Serv
    1.03
    Graph
    1.02
    Provider
    1.01
    Setup
    1.01
    ools
    1.00
    Activations Density 0.271%

    No Known Activations