© 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. 18742
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Got" or "got"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "got"

    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
     inhabit
    -0.60
     depiction
    -0.57
     Sacrifice
    -0.57
     Madness
    -0.56
     Archdemon
    -0.56
    velt
    -0.56
     endeavour
    -0.56
     exhibit
    -0.56
    mare
    -0.54
     dors
    -0.54
    POSITIVE LOGITS
     rid
    1.28
    cloneembedreportprint
    0.99
    cha
    0.97
     acquainted
    0.91
     lucky
    0.87
    DragonMagazine
    0.84
    ActionCode
    0.80
    istical
    0.80
     bitten
    0.78
    acqu
    0.78
    Activations Density 0.093%

    No Known Activations