Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43376
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Epic" in the context of gaming, particularly related to the Unreal Engine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    442
    +0.10
    0.5%
    343
    +0.09
    0.4%
    715
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.10
    0.01
    670
    +0.09
    0.01
    166
    +0.09
    0.01
    Negative Logits
    creen
    -0.81
    eering
    -0.74
    atan
    -0.72
    gotten
    -0.71
    teenth
    -0.71
    âĶĢ
    -0.69
     Jagu
    -0.67
     sovere
    -0.67
    apy
    -0.66
    mosp
    -0.66
    POSITIVE LOGITS
    urious
    1.10
    urus
    0.92
    ulously
    0.84
    Draft
    0.80
    ension
    0.77
     Engine
    0.77
     Tradable
    0.76
    enter
    0.76
    ortunately
    0.71
     Draft
    0.70
    Activations Density 0.010%

    No Known Activations