© 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. 6-RES-JB
    11. 1005
    Prev
    Next
    INDEX
    Explanations

    references to the pop singer Britney Spears

    oai_token-act-pair · gpt-3.5-turbo

    references to British individuals, particularly those named "Brit" or "Britt."

    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
    orse
    -0.73
    rugged
    -0.71
    Rand
    -0.67
    ermott
    -0.67
     vein
    -0.66
    CVE
    -0.66
    externalActionCode
    -0.64
    orf
    -0.64
    Origin
    -0.63
    orses
    -0.63
    POSITIVE LOGITS
    ney
    1.04
    neau
    0.97
    ches
    0.93
    ular
    0.90
    neys
    0.89
    isher
    0.87
    ishers
    0.84
    nell
    0.84
    rix
    0.79
    nia
    0.78
    Activations Density 0.038%

    No Known Activations