© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences indicating personal experiences and reflections

    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
    218
    +0.17
    0.8%
    608
    +0.14
    0.6%
    123
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.17
    0.03
    218
    +0.14
    0.02
    608
    +0.11
    0.02
    Negative Logits
     condemns
    -0.63
    Introduced
    -0.61
    âĤ¬
    -0.59
     includ
    -0.59
     Detected
    -0.59
     predecessors
    -0.59
     conveyed
    -0.58
    erence
    -0.58
    geist
    -0.57
    \'
    -0.57
    POSITIVE LOGITS
     trouble
    1.04
    itialized
    0.86
     mischief
    0.81
     bed
    0.76
     contention
    0.75
     orbit
    0.72
     grips
    0.72
     hypers
    0.71
     puberty
    0.71
    ked
    0.71
    Activations Density 0.037%

    No Known Activations