© 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 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. 6-RES-JB
    11. 8003
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "While" followed by a high activation word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that introduce contrasting or qualifying statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rium
    -0.80
    atron
    -0.78
    aer
    -0.70
    elled
    -0.70
    illet
    -0.69
    isable
    -0.69
    tnc
    -0.69
    enter
    -0.68
    omet
    -0.67
    ulnerable
    -0.67
    POSITIVE LOGITS
     acknowledging
    1.12
     browsing
    0.96
     researching
    0.95
     conced
    0.91
     discussing
    0.89
     agreeing
    0.83
     respecting
    0.82
     dismissing
    0.79
     mentioning
    0.79
     commenting
    0.79
    Activations Density 0.050%

    No Known Activations