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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 9046
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Vir" and related variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "vir" or "Vir," indicating a focus on virility, virulence, and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.91
    uyomi
    -0.82
    cedented
    -0.78
     quarters
    -0.73
    OWER
    -0.72
    ĨĴ
    -0.72
    ļé
    -0.69
    orative
    -0.66
     Defenders
    -0.64
    mare
    -0.64
    POSITIVE LOGITS
    gil
    1.14
    ulence
    1.07
    ulent
    1.05
    gins
    1.01
    cles
    0.96
    idian
    0.88
    neum
    0.84
    iform
    0.83
    apore
    0.82
    iously
    0.81
    Activations Density 0.014%

    No Known Activations