© 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. 22629
    Prev
    Next
    INDEX
    Explanations

    the term "first-hand" or variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to firsthand experiences or testimonies

    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
     Tant
    -0.66
     Gould
    -0.61
    endo
    -0.61
    enegger
    -0.61
    illas
    -0.60
    âĶģ
    -0.60
    ucl
    -0.59
     Doomsday
    -0.57
     Canaver
    -0.57
    Downloadha
    -0.56
    POSITIVE LOGITS
     responders
    1.18
     baseman
    1.10
     impressions
    1.04
     impression
    1.00
     glance
    0.90
     timers
    0.86
     respond
    0.84
     ancest
    0.81
     aid
    0.81
     blush
    0.80
    Activations Density 0.065%

    No Known Activations