© 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. 7-RES-JB
    11. 1605
    Prev
    Next
    INDEX
    Explanations

    references to different aspects of gameplay

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gameplay and associated mechanics in video game discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.85
     Luther
    -0.76
    hood
    -0.75
    vard
    -0.69
    geries
    -0.66
    thening
    -0.66
    ns
    -0.65
     wildfire
    -0.64
    eous
    -0.64
     bapt
    -0.63
    POSITIVE LOGITS
    halla
    1.02
    GROUND
    0.95
     mechanics
    0.90
    PLAY
    0.89
     gameplay
    0.84
    testers
    0.84
     enh
    0.83
    testing
    0.79
     footage
    0.79
     glitches
    0.77
    Activations Density 0.024%

    No Known Activations