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 3072
    5. 8-RES_FS3072-JB
    6. 1132
    Prev
    Next
    INDEX
    Explanations

    information related to political elections and government activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    488
    +0.10
    0.5%
    470
    +0.10
    0.5%
    350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.10
    0.10
    488
    +0.10
    0.09
    224
    +0.10
    0.09
    Negative Logits
    obyl
    -0.83
    sterdam
    -0.79
     explorers
    -0.73
     horm
    -0.72
     Cargo
    -0.72
    ĸļ
    -0.71
     downtime
    -0.69
     crate
    -0.67
     decomp
    -0.65
     overload
    -0.65
    POSITIVE LOGITS
    election
    1.61
     votes
    1.51
     voters
    1.51
     Voters
    1.49
     elections
    1.47
     Elections
    1.47
     ballot
    1.46
    vote
    1.46
     election
    1.46
     vote
    1.45
    Activations Density 2.493%

    No Known Activations