© 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. 7936
    Prev
    Next
    INDEX
    Explanations

    references to temporal sequences and events in a narrative context

    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
    225
    +0.10
    0.5%
    678
    +0.09
    0.4%
    703
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.04
    223
    +0.09
    0.04
    493
    +0.09
    0.03
    Negative Logits
    ongo
    -0.69
    oria
    -0.65
    olute
    -0.63
    ees
    -0.61
    ibaba
    -0.60
    ORN
    -0.60
    ken
    -0.59
    Listener
    -0.58
    phabet
    -0.57
    hemy
    -0.57
    POSITIVE LOGITS
     way
    0.76
     day
    0.73
    til
    0.72
     week
    0.70
     morning
    0.70
     weekend
    0.68
     semester
    0.66
     mornings
    0.66
     furthe
    0.65
     night
    0.65
    Activations Density 0.167%

    No Known Activations