© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14603
    Prev
    Next
    INDEX
    Explanations

    references to the video game "Splatoon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Splatoon" game or its related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grain
    -0.67
     GF
    -0.67
     Ples
    -0.65
    ById
    -0.64
     lact
    -0.64
     pall
    -0.62
     ment
    -0.62
     concess
    -0.59
     legs
    -0.59
    FW
    -0.59
    POSITIVE LOGITS
    icago
    1.06
    ioch
    0.91
    urai
    0.90
    xual
    0.88
    anooga
    0.84
    shi
    0.82
    ouston
    0.82
    anan
    0.81
    waukee
    0.81
    atche
    0.79
    Activations Density 0.025%

    No Known Activations