© 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. 3-RES-JB
    11. 6184
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics and actions, particularly focusing on the concept of a player taking a turn

    oai_token-act-pair · gpt-3.5-turbo

    references to gameplay mechanics involving turns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.77
    ainers
    -0.73
    capacity
    -0.72
    è¦ļéĨĴ
    -0.71
    ropolitan
    -0.68
    namese
    -0.67
    aph
    -0.66
    hered
    -0.65
     Intake
    -0.64
    aps
    -0.63
    POSITIVE LOGITS
    turn
    0.85
    about
    0.79
    edit
    0.78
    terday
    0.75
    overs
    0.74
    buck
    0.72
    coat
    0.70
    abouts
    0.66
    around
    0.63
     shif
    0.63
    Activations Density 0.033%

    No Known Activations