© 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. 4-RES-JB
    11. 8617
    Prev
    Next
    INDEX
    Explanations

    phrases related to time of day or time management

    oai_token-act-pair · gpt-3.5-turbo

    instances of staying awake late and managing temperature or timing in various contexts

    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
    çīĪ
    -0.68
     Cosponsors
    -0.66
    xtap
    -0.54
     acron
    -0.52
    quote
    -0.52
    authors
    -0.51
    Clar
    -0.51
    æ©Ł
    -0.50
    Ted
    -0.49
    CONCLUS
    -0.49
    POSITIVE LOGITS
     anymore
    0.62
     meals
    0.60
     hassle
    0.59
     undet
    0.59
     sleep
    0.57
     snack
    0.55
     meal
    0.55
     sweets
    0.55
     outdoors
    0.55
     clothes
    0.53
    Activations Density 2.697%

    No Known Activations