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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7511
    Prev
    Next
    INDEX
    Explanations

    phrases related to cricket bowling

    oai_token-act-pair · gpt-3.5-turbo

    sports terminology and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Lyft
    -0.97
     Neighborhood
    -0.91
     neighborhoods
    -0.89
    owntown
    -0.89
     Byzantine
    -0.87
     MTA
    -0.85
     Downtown
    -0.85
    oros
    -0.84
     Orthodox
    -0.82
     privatization
    -0.80
    POSITIVE LOGITS
     cricket
    1.87
     Cricket
    1.70
     batting
    1.57
     bowling
    1.52
     Ashes
    1.49
     bats
    1.48
     Tests
    1.41
     innings
    1.39
     Pakistan
    1.35
    Pakistan
    1.34
    Activations Density 0.265%

    No Known Activations