© 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. 11-RES-JB
    11. 20527
    Prev
    Next
    INDEX
    Explanations

    mentions of the ''World Cup''

    oai_token-act-pair · gpt-3.5-turbo

    references to various World Cup events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.83
    pelled
    -0.81
    shown
    -0.76
    imaru
    -0.76
    terday
    -0.75
    ãĤ¨ãĥ«
    -0.73
    bart
    -0.72
    nu
    -0.70
    pie
    -0.70
    argon
    -0.70
    POSITIVE LOGITS
     finals
    1.24
     Finals
    1.21
     qualifiers
    1.19
     qualifier
    1.19
     Playoffs
    1.18
     qualifying
    1.09
     Qual
    1.09
     Final
    1.08
     semifinals
    1.05
     final
    1.01
    Activations Density 0.053%

    No Known Activations