© 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. 1-RES-JB
    11. 6503
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "While"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "While"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isable
    -0.81
    ISE
    -0.75
    ise
    -0.70
    iotic
    -0.68
    omet
    -0.67
    ding
    -0.67
    oded
    -0.66
    aer
    -0.66
    atron
    -0.64
    urable
    -0.64
    POSITIVE LOGITS
     acknowledging
    0.81
     researching
    0.81
     commenting
    0.74
     browsing
    0.72
     conced
    0.71
     discussing
    0.70
    catentry
    0.70
     attending
    0.69
     compiling
    0.69
     agreeing
    0.68
    Activations Density 0.024%

    No Known Activations