© 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. 8-RES-JB
    11. 17789
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparing for various activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "preparing for" followed by various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ware
    -0.79
    taboola
    -0.75
    gnu
    -0.71
    hai
    -0.69
    framework
    -0.68
    eled
    -0.63
     stole
    -0.63
    esthetic
    -0.61
    weed
    -0.60
    ér
    -0.60
    POSITIVE LOGITS
     conting
    1.03
     impending
    0.90
     eventual
    0.89
     future
    0.88
     battle
    0.87
     tomorrow
    0.86
     contingency
    0.81
     passage
    0.80
     disaster
    0.79
     takeoff
    0.76
    Activations Density 0.143%

    No Known Activations