© 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. 11390
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategic decision-making and game elements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to gaming, economics, and strategy

    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
     overseen
    -0.71
    ©¶æ
    -0.67
    olitan
    -0.65
     spearheaded
    -0.62
     undertook
    -0.62
     preceded
    -0.61
     pioneered
    -0.60
     championed
    -0.60
     recently
    -0.59
     convened
    -0.58
    POSITIVE LOGITS
     xp
    0.90
     useless
    0.89
     disadvantage
    0.84
     headache
    0.79
    advant
    0.78
     alot
    0.78
     advantage
    0.76
     worthless
    0.76
     undesirable
    0.75
     bonus
    0.75
    Activations Density 0.716%

    No Known Activations