© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 897
    Prev
    Next
    INDEX
    Explanations

    information related to historical events, specifically around taxes, government revenue, and notable individuals from the past

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    87
    +0.22
    1.1%
    756
    +0.15
    0.7%
    763
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.22
    -0.05
    756
    +0.15
    -0.04
    659
    +0.10
    0.06
    Negative Logits
    VPN
    -0.85
    Uber
    -0.81
     Xiaomi
    -0.79
     veggies
    -0.78
    ï¸ı
    -0.76
     Lyft
    -0.75
     Snapchat
    -0.74
    ratom
    -0.73
     emoji
    -0.72
    ðŁ
    -0.72
    POSITIVE LOGITS
     1909
    1.07
     1912
    1.06
     postwar
    1.06
     1929
    1.06
     1946
    1.04
    oslov
    1.04
     1932
    1.04
     1936
    1.04
     1939
    1.03
     1938
    1.02
    Activations Density 2.165%

    No Known Activations