© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    phrases related to labor rights and working conditions

    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
    420
    +0.13
    0.6%
    575
    +0.12
    0.6%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.03
    420
    +0.12
    0.03
    440
    +0.11
    0.02
    Negative Logits
    olic
    -0.76
    croft
    -0.72
    las
    -0.72
     Viz
    -0.69
    forth
    -0.68
    laus
    -0.67
     BCC
    -0.66
     Buckingham
    -0.65
     Flavoring
    -0.65
     Ukrain
    -0.65
    POSITIVE LOGITS
    worker
    1.04
    workers
    1.00
     unions
    0.95
     ethic
    0.91
     workers
    0.90
     union
    0.88
     ants
    0.87
     worker
    0.86
     employed
    0.85
    paces
    0.85
    Activations Density 0.047%

    No Known Activations