© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5476
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and institutions

    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
     tempting
    -0.59
     breeze
    -0.57
     skim
    -0.57
     minus
    -0.56
     cheaply
    -0.56
     hits
    -0.56
     popping
    -0.55
     goodbye
    -0.55
     stale
    -0.54
     airs
    -0.54
    POSITIVE LOGITS
     Institute
    0.88
     Consulting
    0.80
     Forensic
    0.80
     Investigative
    0.80
     Association
    0.79
     Archae
    0.79
     Research
    0.77
     Directorate
    0.77
     Veterinary
    0.77
     Telecommunications
    0.77
    Activations Density 0.485%

    No Known Activations