© 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. 9-RES-JB
    11. 2010
    Prev
    Next
    INDEX
    Explanations

    instances of the word "otherwise."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate exceptions or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.72
     Tycoon
    -0.66
     Citiz
    -0.66
    pled
    -0.65
     Nuggets
    -0.64
     Extension
    -0.64
    java
    -0.63
     Osaka
    -0.62
    resa
    -0.62
     oranges
    -0.61
    POSITIVE LOGITS
    SPONSORED
    0.89
     unrem
    0.81
     unavailable
    0.79
     unnoticed
    0.76
     unim
    0.76
     guiActiveUnfocused
    0.76
     behaved
    0.75
    worldly
    0.74
    forth
    0.73
     inaccessible
    0.73
    Activations Density 0.019%

    No Known Activations