© 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. 19496
    Prev
    Next
    INDEX
    Explanations

    words related to challenges, struggles, and negative situations regarding vulnerable groups like children, homeless individuals, and workers

    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
    481
    +0.23
    1.1%
    540
    +0.13
    0.6%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.23
    0.06
    431
    +0.13
    0.04
    713
    +0.11
    0.04
    Negative Logits
     Zamb
    -0.66
     faint
    -0.61
     pasture
    -0.61
     paste
    -0.59
    herry
    -0.58
     Lit
    -0.56
     Jes
    -0.55
     obscurity
    -0.53
    tein
    -0.52
     unpop
    -0.52
    POSITIVE LOGITS
     during
    1.00
     throughout
    0.91
     whilst
    0.86
     regarding
    0.85
    Interstitial
    0.82
    .:
    0.78
     beforehand
    0.76
    ngth
    0.74
     towards
    0.74
     while
    0.73
    Activations Density 0.187%

    No Known Activations