© 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. 9917
    Prev
    Next
    INDEX
    Explanations

    phrases related to the beginning or initiation of an activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss initial experiences or beginnings

    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
    asty
    -0.71
     Canaver
    -0.68
     Replacement
    -0.66
    ruct
    -0.63
    EXT
    -0.61
     Doomsday
    -0.60
    raint
    -0.60
    ritical
    -0.58
     Snyder
    -0.58
    cling
    -0.58
    POSITIVE LOGITS
     baseman
    1.09
     responders
    0.95
     glance
    0.87
     lady
    0.87
     appeared
    0.83
     encountered
    0.81
     conceived
    0.80
     blush
    0.80
     Introduced
    0.76
     introduced
    0.76
    Activations Density 0.037%

    No Known Activations