© 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. 3808
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "While"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce contrasting ideas or conditions

    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
    ISE
    -0.81
    isable
    -0.79
    ise
    -0.77
    aer
    -0.73
    irs
    -0.71
    omet
    -0.70
    iotic
    -0.68
    atron
    -0.68
    romeda
    -0.68
    arse
    -0.67
    POSITIVE LOGITS
     researching
    0.87
     acknowledging
    0.81
     browsing
    0.80
     discussing
    0.77
     compiling
    0.76
     agreeing
    0.76
     commenting
    0.73
     attending
    0.73
    catentry
    0.70
     evaluating
    0.70
    Activations Density 0.034%

    No Known Activations