© 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. 18574
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional impact and personal struggles

    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
    651
    +0.12
    0.5%
    279
    +0.10
    0.5%
    39
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.03
    279
    +0.10
    0.03
    39
    +0.10
    0.02
    Negative Logits
    emort
    -0.94
    edia
    -0.82
    dinand
    -0.81
    egal
    -0.80
    ItemTracker
    -0.79
    ahime
    -0.79
    ategory
    -0.79
    essee
    -0.78
    DragonMagazine
    -0.77
    ociate
    -0.77
    POSITIVE LOGITS
     thereafter
    1.01
    motion
    0.90
    dream
    0.85
     waking
    0.85
     mornings
    0.80
     throughout
    0.73
    night
    0.71
     until
    0.71
     morning
    0.70
     regardless
    0.70
    Activations Density 0.027%

    No Known Activations