© 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. 4-RES-JB
    11. 446
    Prev
    Next
    INDEX
    Explanations

    references related to the name "Borg" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Borg, a fictional group from the Star Trek franchise

    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
    IELD
    -0.86
    ffield
    -0.64
     Appalachian
    -0.63
    ãħĭ
    -0.63
     Flavoring
    -0.62
    PLIED
    -0.61
     Eliot
    -0.60
    ================================================================
    -0.59
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.58
    ulton
    -0.58
    POSITIVE LOGITS
    wana
    1.01
     Borg
    0.96
    uno
    0.94
    esian
    0.85
    haus
    0.81
    isson
    0.81
    leneck
    0.80
    strom
    0.80
    hetti
    0.79
     Yards
    0.79
    Activations Density 0.010%

    No Known Activations