© 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. 8-RES-JB
    11. 18601
    Prev
    Next
    INDEX
    Explanations

    terms related to calendars and scheduling tasks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to calendars and scheduling tools

    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
    amiya
    -0.79
    Downloadha
    -0.76
    amaru
    -0.74
    ARP
    -0.73
    uka
    -0.72
    upon
    -0.70
     Huck
    -0.70
    maxwell
    -0.69
    ibaba
    -0.69
    avery
    -0.69
    POSITIVE LOGITS
     calendars
    1.05
     calendar
    1.04
     Calendar
    1.00
    endar
    0.76
     reminder
    0.71
     entries
    0.71
     appointments
    0.71
     reminders
    0.70
    isphere
    0.69
     Countdown
    0.68
    Activations Density 0.038%

    No Known Activations