Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 16130
    Prev
    Next
    INDEX
    Explanations

    phrases related to the FIFA World Cup

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the World Cup

    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
    */(
    -0.86
    tesy
    -0.78
    cro
    -0.75
    bart
    -0.75
    verified
    -0.74
    ãĤ¨ãĥ«
    -0.73
    ogyn
    -0.70
    utenant
    -0.67
     Anon
    -0.67
    paio
    -0.66
    POSITIVE LOGITS
     qualifiers
    1.04
     Finals
    1.00
     qualifier
    0.94
     finals
    0.92
     qualifying
    0.91
     Qual
    0.87
     Championships
    0.86
     2022
    0.85
     Playoffs
    0.82
     organisers
    0.81
    Activations Density 0.041%

    No Known Activations