© 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. 4-RES-JB
    11. 10487
    Prev
    Next
    INDEX
    Explanations

    mentions of specific video game titles followed by their respective versions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of video game titles and associated content

    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
    meyer
    -0.75
    wcs
    -0.72
    intendent
    -0.71
    rolet
    -0.68
    ierrez
    -0.66
    externalActionCode
    -0.65
    animous
    -0.64
     Byrd
    -0.63
     Clause
    -0.62
    utory
    -0.62
    POSITIVE LOGITS
     Deluxe
    0.79
     Redux
    0.75
    RPG
    0.73
     Ultimate
    0.73
     Interactive
    0.72
    angan
    0.72
    uden
    0.72
     Definitive
    0.71
     onwards
    0.71
     videog
    0.70
    Activations Density 0.069%

    No Known Activations