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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10850
    Prev
    Next
    INDEX
    Explanations

    details about events, including ticket prices, age restrictions, and location instructions

    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
    459
    +0.10
    0.5%
    515
    +0.10
    0.4%
    592
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.10
    0.04
    609
    +0.10
    0.05
    677
    +0.09
    0.04
    Negative Logits
    âĹ¼
    -0.96
     billions
    -0.83
    ãĥŀ
    -0.80
    ãĥķãĤ¡
    -0.79
     trillions
    -0.79
     Turing
    -0.74
    ģĸ
    -0.72
    weak
    -0.72
     analys
    -0.71
    ãĤ¶
    -0.71
    POSITIVE LOGITS
     seating
    1.08
     Guests
    1.04
     Admission
    1.02
     admission
    1.02
     beverages
    1.02
     picnic
    0.98
     patrons
    0.96
     complimentary
    0.96
     guests
    0.95
     amenities
    0.94
    Activations Density 0.858%

    No Known Activations