© 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. 18523
    Prev
    Next
    INDEX
    Explanations

    phrases related to narrative storytelling or instructional information

    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
    749
    +0.12
    0.6%
    628
    +0.12
    0.6%
    610
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.12
    0.02
    210
    +0.12
    0.02
    222
    +0.12
    0.01
    Negative Logits
     nonetheless
    -0.90
    etheless
    -0.81
    patrick
    -0.65
    stress
    -0.64
     nevertheless
    -0.63
    pei
    -0.62
    inger
    -0.62
    esan
    -0.62
    rect
    -0.61
    cerpt
    -0.59
    POSITIVE LOGITS
     aesthetics
    0.61
     paycheck
    0.59
     pian
    0.57
    omical
    0.57
    ifiable
    0.57
     aest
    0.56
     fixme
    0.55
     guiActive
    0.55
     visually
    0.55
    DERR
    0.54
    Activations Density 0.109%

    No Known Activations