© 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. 10-RES-JB
    11. 4629
    Prev
    Next
    INDEX
    Explanations

    words that contain the common subsequence "wo"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Wo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horizont
    -0.94
     Spiegel
    -0.75
    Ú
    -0.66
    âĸ¬
    -0.64
    âĸ¬âĸ¬
    -0.63
    ++++++++++++++++
    -0.63
    mite
    -0.62
     flares
    -0.61
     simultane
    -0.61
     Phantom
    -0.60
    POSITIVE LOGITS
    ollen
    1.22
    ofer
    1.15
    ocom
    1.10
    ollah
    1.09
    efully
    1.05
    onder
    1.05
    eful
    1.04
    olly
    1.01
    orst
    0.93
    ongs
    0.89
    Activations Density 0.031%

    No Known Activations