© 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. 2-RES-JB
    11. 15278
    Prev
    Next
    INDEX
    Explanations

    the word "either"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a choice or option between alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iliate
    -0.83
    Indian
    -0.80
    uyomi
    -0.76
    orsi
    -0.69
    earchers
    -0.66
    displayText
    -0.66
     Azerbaijan
    -0.65
    oshenko
    -0.64
    sburgh
    -0.64
    OVER
    -0.64
    POSITIVE LOGITS
     lighthouse
    0.76
    hid
    0.72
     Mk
    0.70
    ctrl
    0.67
    \\\\
    0.67
     α
    0.64
    jar
    0.62
    ////
    0.62
    enment
    0.62
     Libraries
    0.61
    Activations Density 0.000%

    No Known Activations