© 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. 19452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific technical features or instructions related to a device or technology

    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
    603
    +0.11
    0.5%
    706
    +0.11
    0.5%
    418
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.11
    0.05
    706
    +0.11
    0.05
    582
    +0.10
    0.04
    Negative Logits
    agin
    -0.74
    ulous
    -0.70
    abal
    -0.69
    aido
    -0.69
    oslov
    -0.67
    elman
    -0.66
    incial
    -0.65
    ulture
    -0.65
    zzi
    -0.65
    hack
    -0.64
    POSITIVE LOGITS
    soever
    1.25
     encountering
    0.99
     transitioning
    0.96
     confronted
    0.92
     viewed
    0.92
     calculating
    0.89
     exiting
    0.85
     faced
    0.85
     pressed
    0.85
     evaluating
    0.82
    Activations Density 0.118%

    No Known Activations