© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22210
    Prev
    Next
    INDEX
    Explanations

    terms related to tabletop role-playing games and their mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    430
    +0.11
    0.5%
    160
    +0.10
    0.5%
    400
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.03
    288
    +0.10
    0.03
    76
    +0.10
    0.02
    Negative Logits
    bed
    -0.79
    headed
    -0.72
    nel
    -0.70
     anten
    -0.69
    igne
    -0.69
    lah
    -0.68
    Īè
    -0.68
     vou
    -0.68
    mediately
    -0.67
    aye
    -0.67
    POSITIVE LOGITS
     tabletop
    1.28
     Pathfinder
    1.16
     RPG
    1.11
     RPGs
    1.05
    ampunk
    1.01
    RPG
    1.01
     Dice
    0.98
     dice
    0.96
     Lovecraft
    0.96
    ebook
    0.94
    Activations Density 0.107%

    No Known Activations