© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18579
    Prev
    Next
    INDEX
    Explanations

    dates or events described with a premise starting with "After."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "After" used 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
     accordingly
    -0.90
    itiz
    -0.76
    ogether
    -0.74
     versa
    -0.71
     thereto
    -0.70
     etc
    -0.65
     eg
    -0.65
    "}],"
    -0.65
     therefore
    -0.65
     vou
    -0.64
    POSITIVE LOGITS
     Tropical
    0.81
     Hurricane
    0.80
     wildfires
    0.76
     Thanksgiving
    0.75
     Donald
    0.75
     celebrating
    0.74
     NASCAR
    0.74
     Tonight
    0.74
     announcing
    0.73
     bombshell
    0.73
    Activations Density 0.257%

    No Known Activations