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. 18422
    Prev
    Next
    INDEX
    Explanations

    phrases related to the soccer club "Real Madrid."

    oai_token-act-pair · gpt-3.5-turbo

    references to the football club Real Madrid

    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
    xual
    -0.86
    avorite
    -0.78
     Sawyer
    -0.74
    rav
    -0.70
    URR
    -0.69
    hire
    -0.68
    cake
    -0.68
     DRAG
    -0.66
    ebook
    -0.64
    atton
    -0.63
    POSITIVE LOGITS
    istically
    1.35
    istic
    1.26
    ignment
    1.25
     Estate
    1.22
     estate
    1.15
     Madrid
    1.14
    idad
    1.09
    isation
    1.07
    estate
    1.07
    tek
    1.07
    Activations Density 0.025%

    No Known Activations