© 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. 24311
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making and control over circumstances

    oai_token-act-pair · gpt-4o-miniTriggered 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
    480
    +0.44
    2.3%
    447
    +0.19
    1.0%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.44
    0.09
    266
    +0.19
    0.07
    480
    +0.13
    0.02
    Negative Logits
    ãĤ´ãĥ³
    -0.65
    eatures
    -0.63
    anwhile
    -0.57
     headlined
    -0.56
     fortunately
    -0.56
    quartered
    -0.56
    Compar
    -0.56
    luster
    -0.54
     luckily
    -0.54
     Vaugh
    -0.54
    POSITIVE LOGITS
     oneself
    0.89
     them
    0.74
     your
    0.72
     yourself
    0.72
     him
    0.69
     ourselves
    0.66
     yourselves
    0.64
    igate
    0.64
     somebody
    0.63
     anything
    0.61
    Activations Density 0.536%

    No Known Activations