© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    mentions of "GTA" and its related terms, like DLC, gameplay elements, and specific locations within the game

    oai_token-act-pair · gpt-3.5-turbo

    references to the Grand Theft Auto game series

    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
    asin
    -0.94
    tnc
    -0.91
    cius
    -0.81
    zac
    -0.75
    shr
    -0.75
    imental
    -0.75
    ERC
    -0.74
    istry
    -0.73
    ogly
    -0.73
    erker
    -0.72
    POSITIVE LOGITS
     Wasteland
    0.94
     Fallout
    0.91
     Shelter
    0.91
    NV
    0.88
     IV
    0.85
     Online
    0.80
     GTA
    0.79
     Vegas
    0.77
     Vault
    0.77
     Tactics
    0.75
    Activations Density 0.050%

    No Known Activations