© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7916
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Virgil" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Vir" or variations of it

    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
    */(
    -0.83
    cedented
    -0.80
    OWER
    -0.74
     Unch
    -0.73
    IELD
    -0.71
     quarters
    -0.70
    ĨĴ
    -0.67
    ographical
    -0.67
     Merrill
    -0.66
    uyomi
    -0.65
    POSITIVE LOGITS
    gil
    1.30
    gins
    1.24
    ulence
    1.08
    cles
    1.06
    ulent
    0.95
    anus
    0.94
    ility
    0.93
    nces
    0.92
    tex
    0.92
    bis
    0.92
    Activations Density 0.033%

    No Known Activations