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. 11-RES-JB
    6. 18714
    Prev
    Next
    INDEX
    Explanations

    sports-related activities and games

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to sports and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongevity
    -0.68
    ¿½
    -0.68
    icht
    -0.65
     arrivals
    -0.65
    gement
    -0.65
     Employ
    -0.64
     arrival
    -0.63
     Publishers
    -0.63
    igslist
    -0.63
    ablishment
    -0.62
    POSITIVE LOGITS
     games
    1.21
     roles
    1.08
     Mahjong
    1.06
     role
    1.06
    games
    1.03
     game
    0.99
     videog
    0.94
     chess
    0.91
     basketball
    0.89
     cricket
    0.89
    Activations Density 0.153%

    No Known Activations