© 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. 17808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "non" in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "non-."

    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
     Tycoon
    -0.99
     Showdown
    -0.81
     Banner
    -0.80
     Oaks
    -0.79
     Cobra
    -0.78
    hower
    -0.75
     Gardens
    -0.74
     Plate
    -0.73
     McGee
    -0.72
     Sparrow
    -0.72
    POSITIVE LOGITS
    etheless
    1.10
    chal
    1.10
    fiction
    1.09
    linear
    1.07
    epad
    1.04
    zero
    1.04
    technical
    1.03
    profit
    1.02
    verbal
    1.00
    aligned
    0.98
    Activations Density 0.033%

    No Known Activations