© 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. 4-RES-JB
    11. 22268
    Prev
    Next
    INDEX
    Explanations

    phrases related to mythical clans and hidden secrets

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to mythical or fantasy elements

    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
    ilater
    -0.92
     incent
    -0.83
    mercial
    -0.82
     nodd
    -0.81
     Zucker
    -0.79
    Hamilton
    -0.77
     MSNBC
    -0.75
     endors
    -0.74
    endment
    -0.73
     CNBC
    -0.73
    POSITIVE LOGITS
    sword
    1.24
     mage
    1.22
     Undead
    1.17
     Elves
    1.17
     dwarves
    1.16
     mages
    1.16
     sorce
    1.13
     goblin
    1.11
     sorcerer
    1.07
     Clan
    1.07
    Activations Density 1.184%

    No Known Activations