© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    references to the video game "Grand Theft Auto"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Grand Theft Auto (GTA) video game 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
    ãĤ·ãĥ£
    -0.77
    cription
    -0.75
    nown
    -0.73
    usra
    -0.72
    anda
    -0.72
    abol
    -0.71
    itsch
    -0.71
    nir
    -0.71
    Downloadha
    -0.70
    idas
    -0.70
    POSITIVE LOGITS
     GTA
    1.13
     Theft
    0.85
     Wasteland
    0.74
     Andreas
    0.72
     Uncharted
    0.72
    LLOW
    0.69
     Vault
    0.68
     Fallout
    0.68
     slug
    0.67
     videog
    0.66
    Activations Density 0.017%

    No Known Activations