© 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. 10-RES-JB
    11. 13758
    Prev
    Next
    INDEX
    Explanations

    the word "or" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases presenting choices or dichotomies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.65
     corridors
    -0.64
    ascus
    -0.62
     precincts
    -0.62
     levers
    -0.61
    iola
    -0.58
    ourses
    -0.58
    arks
    -0.56
     districts
    -0.55
     Lerner
    -0.55
    POSITIVE LOGITS
    acle
    1.39
    chard
    1.30
    ifice
    1.29
    Else
    1.28
    nam
    1.24
    acles
    1.23
    chid
    1.23
    acular
    1.16
    nery
    1.10
    lando
    1.04
    Activations Density 0.071%

    No Known Activations