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. 6-RES-JB
    6. 6591
    Prev
    Next
    INDEX
    Explanations

    references to football clubs, particularly Bayern Munich

    oai_token-act-pair · gpt-3.5-turbo

    mentions of soccer teams and related sports terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.86
    earchers
    -0.82
    yip
    -0.82
    andering
    -0.78
    ilver
    -0.77
    regon
    -0.76
    ippery
    -0.76
    owder
    -0.76
    othy
    -0.75
    motion
    -0.74
    POSITIVE LOGITS
     Munich
    1.61
     Mü
    1.32
     Dortmund
    0.95
     Bayern
    0.94
     Guardiola
    0.91
     Bundesliga
    0.87
    ische
    0.84
     Bav
    0.83
    stadt
    0.81
     Lever
    0.80
    Activations Density 0.041%

    No Known Activations