Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7370
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaming, such as upgrades, battles, puzzles, and gameplay features

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contextual significance

    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
    ileaks
    -0.78
     neighb
    -0.73
    terday
    -0.68
     union
    -0.68
    lehem
    -0.67
     divest
    -0.66
    cules
    -0.66
    utonium
    -0.66
     mosqu
    -0.65
    ury
    -0.63
    POSITIVE LOGITS
    Gameplay
    1.19
    Players
    1.05
    Characters
    0.93
    Game
    0.93
    Trivia
    0.88
    Tact
    0.88
    Xbox
    0.88
    Original
    0.87
    Gallery
    0.86
    Developer
    0.85
    Activations Density 0.423%

    No Known Activations