© 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. 19646
    Prev
    Next
    INDEX
    Explanations

    phrases related to traditional methods and practices

    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
    373
    +0.11
    0.5%
    131
    +0.10
    0.5%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    622
    +0.11
    0.02
    284
    +0.10
    0.02
    435
    +0.09
    0.01
    Negative Logits
    SPONSORED
    -0.89
    pta
    -0.84
    Rated
    -0.79
    erto
    -0.78
    abases
    -0.76
    leased
    -0.75
    emis
    -0.75
    endant
    -0.74
    pedia
    -0.73
    answer
    -0.73
    POSITIVE LOGITS
     fashioned
    1.26
    fashioned
    0.94
     ol
    0.83
     brute
    0.83
     sle
    0.79
     fun
    0.78
     gentleman
    0.76
     Victorian
    0.74
     classic
    0.74
     trickle
    0.74
    Activations Density 0.058%

    No Known Activations