© 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 24576
    9. 8-RES_FS24576-JB
    11. 20452
    Prev
    Next
    INDEX
    Explanations

    news events and controversies involving individuals in public positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    679
    +0.14
    0.7%
    440
    +0.11
    0.5%
    480
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.12
    440
    +0.11
    0.11
    679
    +0.11
    0.12
    Negative Logits
    liest
    -0.81
    ŃĶ
    -0.73
     extinct
    -0.69
     dips
    -0.68
    ikuman
    -0.68
     dividend
    -0.66
     defe
    -0.64
     nodd
    -0.63
     salute
    -0.63
     transporter
    -0.63
    POSITIVE LOGITS
    SPONSORED
    1.13
     Specifically
    1.11
     Instead
    1.05
     Additionally
    1.03
     Ironically
    1.02
     Critics
    1.00
     Similarly
    0.99
     Previously
    0.98
     Ultimately
    0.96
     According
    0.96
    Activations Density 0.451%

    No Known Activations