© 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. 19682
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal thoughts, beliefs, and motivations

    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
    453
    +0.10
    0.5%
    206
    +0.10
    0.5%
    404
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.10
    0.03
    531
    +0.10
    0.03
    327
    +0.10
    0.03
    Negative Logits
    Ha
    -0.72
    displayText
    -0.68
     latitude
    -0.65
     Principles
    -0.63
     VIDEOS
    -0.63
    utenberg
    -0.61
     Simulator
    -0.59
    TPP
    -0.58
    odore
    -0.58
     Facts
    -0.58
    POSITIVE LOGITS
     us
    0.97
     me
    0.82
     him
    0.75
     sear
    0.69
     employers
    0.69
     haunt
    0.67
    tered
    0.67
    ters
    0.66
    umin
    0.66
    awed
    0.66
    Activations Density 0.132%

    No Known Activations