© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14884
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Soccer"

    oai_token-act-pair · gpt-3.5-turbo

    references to soccer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appar
    -0.63
     afford
    -0.62
    abeth
    -0.60
     doses
    -0.59
    umph
    -0.59
     dishon
    -0.59
     careful
    -0.59
     Ca
    -0.58
     molten
    -0.57
     commanded
    -0.57
    POSITIVE LOGITS
     Soccer
    4.27
     soccer
    2.15
     Tennis
    1.90
     Baseball
    1.87
     Football
    1.85
     Hockey
    1.76
    Football
    1.75
     Basketball
    1.75
    Soc
    1.62
     NASL
    1.60
    Activations Density 0.006%

    No Known Activations