© 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. 6-RES-JB
    11. 3006
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Sword" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "sword."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.78
    eret
    -0.72
    Organ
    -0.71
    ITIES
    -0.70
    greSQL
    -0.70
    ipolar
    -0.69
    EMBER
    -0.69
     Organizations
    -0.65
    ODE
    -0.65
     Cellular
    -0.64
    POSITIVE LOGITS
    fish
    1.06
     swall
    1.00
    breaker
    0.95
     blades
    0.94
    manship
    0.94
     swords
    0.91
    fights
    0.91
     wielded
    0.90
    lance
    0.90
    fighting
    0.89
    Activations Density 0.023%

    No Known Activations