© 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. 11-RES-JB
    11. 4781
    Prev
    Next
    INDEX
    Explanations

    phrases indicating it is time to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply a call to action or a suggestion to change or do something

    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
    hent
    -0.75
     Palest
    -0.70
    76561
    -0.69
    furt
    -0.67
    secret
    -0.65
    ridden
    -0.65
    majority
    -0.64
    ICLE
    -0.62
    mails
    -0.61
    forced
    -0.61
    POSITIVE LOGITS
     revisit
    1.36
     rethink
    1.27
     rejoice
    1.16
     reconsider
    1.15
     retire
    1.08
     celebrate
    1.08
     revise
    1.03
     rename
    0.97
     reclaim
    0.96
     reass
    0.96
    Activations Density 0.226%

    No Known Activations