© 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. 19728
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms or concepts, potentially in a business context

    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
    447
    +0.22
    1.0%
    430
    +0.11
    0.5%
    633
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.10
    679
    +0.11
    0.09
    454
    +0.10
    0.07
    Negative Logits
     concess
    -0.88
     eas
    -0.75
    catentry
    -0.73
     maxim
    -0.72
    othe
    -0.71
    esse
    -0.71
    ratulations
    -0.71
    iman
    -0.71
    auld
    -0.69
    aunder
    -0.69
    POSITIVE LOGITS
     Worse
    1.12
     Firstly
    1.10
     Ratings
    1.06
     Despite
    1.02
     Luckily
    1.01
     Fortunately
    1.00
     Thankfully
    0.99
     Literally
    0.98
     Its
    0.97
     Especially
    0.97
    Activations Density 0.428%

    No Known Activations