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. 37126
    Prev
    Next
    INDEX
    Explanations

    mentions of the Xbox console and its various iterations and features

    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
    447
    +0.13
    0.6%
    343
    +0.12
    0.6%
    436
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.13
    0.01
    241
    +0.12
    0.01
    594
    +0.10
    0.01
    Negative Logits
    mony
    -0.77
    ãĤ¡
    -0.77
    ãĥ¼ãĤ¯
    -0.76
     volunt
    -0.75
    trump
    -0.74
    atory
    -0.74
    ãĥ£
    -0.73
    arial
    -0.72
    rador
    -0.72
    actionDate
    -0.72
    POSITIVE LOGITS
    ®,
    0.84
    ®
    0.81
     Defender
    0.81
     Dimensions
    0.81
     Controller
    0.80
     consoles
    0.77
    âĦ¢
    0.75
     Anniversary
    0.74
     Storage
    0.72
     X
    0.71
    Activations Density 0.011%

    No Known Activations