© 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. 1-RES-JB
    11. 2614
    Prev
    Next
    INDEX
    Explanations

    words related to various objects or actions associated with ducts and restraints like handcuffs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duct systems and the act of restraining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Summers
    -0.85
    ãĥī
    -0.84
     Ital
    -0.77
     Anders
    -0.75
     Weekly
    -0.74
     DOI
    -0.73
    âĿ
    -0.72
     Edited
    -0.72
     Orth
    -0.72
     Bold
    -0.71
    POSITIVE LOGITS
     duct
    1.50
    yrinth
    1.03
    perature
    0.98
    shed
    0.90
    iosyn
    0.90
    istry
    0.90
    ĪĴ
    0.89
     sockets
    0.87
    anooga
    0.86
    tube
    0.84
    Activations Density 0.014%

    No Known Activations