© 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. 20549
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions or actions that are contingent on prior events

    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
    emale
    -0.70
    alde
    -0.66
    cised
    -0.62
    acial
    -0.60
    apolis
    -0.57
    akedown
    -0.55
    allel
    -0.55
    FOX
    -0.54
    idal
    -0.54
     Cham
    -0.54
    POSITIVE LOGITS
    something
    1.78
    anything
    1.65
     things
    1.63
     something
    1.60
    things
    1.57
    nothing
    1.56
    THING
    1.56
     Something
    1.55
     Things
    1.54
     stuff
    1.51
    Activations Density 0.363%

    No Known Activations