© 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. 11-RES-JB
    11. 20651
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "that" in various contexts

    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
    apolis
    -0.86
    hops
    -0.82
    busters
    -0.82
    ainers
    -0.81
    AMS
    -0.79
    hens
    -0.78
    okers
    -0.77
     Roose
    -0.77
    rypt
    -0.77
    inces
    -0.76
    POSITIVE LOGITS
     translates
    1.02
     happens
    0.98
     entails
    0.96
     person
    0.96
     distinction
    0.95
     determination
    0.95
     same
    0.93
     pesky
    0.93
     particular
    0.90
     knowledge
    0.87
    Activations Density 0.130%

    No Known Activations