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. 4009
    Prev
    Next
    INDEX
    Explanations

    phrases related to playing games or musical instruments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to playing games

    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
    ablishment
    -0.71
    icht
    -0.70
    igslist
    -0.69
     Publishers
    -0.69
    gement
    -0.68
    ¿½
    -0.68
    ortium
    -0.67
     Employ
    -0.65
    ongevity
    -0.65
     Editors
    -0.64
    POSITIVE LOGITS
     games
    1.14
     role
    1.12
     roles
    1.05
     game
    1.01
     poker
    0.91
    games
    0.91
     videog
    0.89
     Mahjong
    0.89
    role
    0.86
     piano
    0.84
    Activations Density 0.165%

    No Known Activations