© 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. 2-RES-JB
    11. 23865
    Prev
    Next
    INDEX
    Explanations

    mentions of the Super Bowl

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Super Bowl

    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
    Reviewer
    -0.88
    STD
    -0.71
    gow
    -0.70
     kindred
    -0.69
     mathemat
    -0.67
    UTC
    -0.67
    IM
    -0.65
     NEC
    -0.64
    akin
    -0.63
    shapeshifter
    -0.63
    POSITIVE LOGITS
     Bowl
    1.27
    bowl
    1.00
    cup
    0.80
     âī¡
    0.77
     Simulator
    0.76
     Tracker
    0.76
     Stadium
    0.75
     Cups
    0.75
    ombat
    0.75
    games
    0.74
    Activations Density 0.008%

    No Known Activations