© 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. 4-RES-JB
    11. 22306
    Prev
    Next
    INDEX
    Explanations

    instances of waiting or going through a period of time or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of waiting or duration

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

    No Comments

    Negative Logits
    APE
    -0.66
    arget
    -0.66
    Member
    -0.65
    MI
    -0.64
    Adapter
    -0.64
     Encyclopedia
    -0.61
    é¾į
    -0.61
    Domain
    -0.60
    JV
    -0.60
     Tie
    -0.59
    POSITIVE LOGITS
     lately
    1.18
     since
    0.92
     recently
    0.86
     previously
    0.83
     awhile
    0.80
     unsuccessfully
    0.76
     hitherto
    0.74
     steady
    0.72
    alysed
    0.71
     successful
    0.69
    Activations Density 0.635%

    No Known Activations