© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5083
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of playing sports or games

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports activities and gameplay

    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
    pora
    -0.75
     Flavoring
    -0.75
    edia
    -0.73
    elight
    -0.65
    pta
    -0.65
    antha
    -0.64
    nor
    -0.62
    sonian
    -0.62
     Scotia
    -0.62
    irement
    -0.61
    POSITIVE LOGITS
     differently
    1.40
     smarter
    1.26
     aggressively
    1.18
     harder
    1.16
     slower
    1.12
     poorly
    1.11
     wisely
    1.07
     efficiently
    1.07
     faster
    1.06
     cautiously
    1.05
    Activations Density 0.208%

    No Known Activations