© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to tradition or traditional practices

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "traditional" and its variants

    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
     Wanted
    -0.75
    upon
    -0.73
     Ferry
    -0.64
    atoon
    -0.64
    rider
    -0.63
     hereafter
    -0.63
     Seat
    -0.63
    mentation
    -0.62
    ————————————————
    -0.61
     Aware
    -0.61
    POSITIVE LOGITS
    arily
    1.03
    ties
    0.90
    ised
    0.87
    izations
    0.85
    ists
    0.82
    IZ
    0.78
    isation
    0.77
    ized
    0.77
     wisdom
    0.77
    ization
    0.77
    Activations Density 0.019%

    No Known Activations