© 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. 10-RES-JB
    11. 3115
    Prev
    Next
    INDEX
    Explanations

    phrases related to in-game actions and conditions

    oai_token-act-pair · gpt-3.5-turbo

    game mechanics related to player interactions and item effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.91
    vet
    -0.79
    iola
    -0.78
    India
    -0.77
    orsche
    -0.73
    Pinterest
    -0.68
    ploma
    -0.67
    èª
    -0.67
     seminars
    -0.67
    ebook
    -0.66
    POSITIVE LOGITS
     respawn
    1.28
     minion
    1.22
     melee
    1.21
     player
    1.16
     enemy
    1.15
     NPCs
    1.14
     Enemies
    1.12
     minions
    1.11
    spawn
    1.10
     Characters
    1.10
    Activations Density 0.307%

    No Known Activations