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. 1141
    Prev
    Next
    INDEX
    Explanations

    locations and events related to law enforcement and criminal 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
    219
    +0.11
    0.5%
    481
    +0.11
    0.5%
    115
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.11
    0.10
    232
    +0.11
    0.11
    65
    +0.10
    0.10
    Negative Logits
    vana
    -0.86
     sacrific
    -0.76
    agonists
    -0.72
    aphael
    -0.71
    akable
    -0.70
    ãĥĻ
    -0.69
    sheet
    -0.65
    onym
    -0.65
    β
    -0.64
    angible
    -0.64
    POSITIVE LOGITS
     County
    1.77
     Township
    1.50
    shire
    1.35
     Heights
    1.33
     Borough
    1.26
     Valley
    1.25
     Parish
    1.24
     Hills
    1.24
     Falls
    1.20
     City
    1.18
    Activations Density 1.245%

    No Known Activations