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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10265
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or preparation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "ready for" followed by a significant event or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ware
    -0.78
    formerly
    -0.72
    æ©Ł
    -0.67
    rated
    -0.66
     Tradable
    -0.66
    nex
    -0.65
     ILCS
    -0.65
    weed
    -0.65
    bourg
    -0.64
     Originally
    -0.64
    POSITIVE LOGITS
     takeoff
    1.06
     emergencies
    1.00
     tomorrow
    0.96
     greatness
    0.94
     conting
    0.91
     battle
    0.90
     Armageddon
    0.90
     eventual
    0.89
     another
    0.86
     showdown
    0.85
    Activations Density 0.176%

    No Known Activations