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. 10-RES-JB
    6. 9683
    Prev
    Next
    INDEX
    Explanations

    references to managerial successes and challenges in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to the career, tactics, and achievements of soccer managers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospons
    -1.03
     Neighbor
    -0.94
    osponsors
    -0.94
    colored
    -0.93
    ADVERTISEMENT
    -0.93
     enrollment
    -0.90
    Hispanic
    -0.90
     ACLU
    -0.88
    GOP
    -0.88
     federally
    -0.87
    POSITIVE LOGITS
     Mourinho
    1.54
     Liverpool
    1.48
     Anfield
    1.42
     Tottenham
    1.42
    Liverpool
    1.40
     Guardiola
    1.39
     Klopp
    1.37
     Wenger
    1.37
     Leicester
    1.35
     Newcastle
    1.31
    Activations Density 0.819%

    No Known Activations