© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7737
    Prev
    Next
    INDEX
    Explanations

    financial and market-related terms

    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
    380
    +0.11
    0.5%
    316
    +0.10
    0.5%
    684
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.03
    512
    +0.10
    0.03
    176
    +0.10
    0.02
    Negative Logits
     Protector
    -0.73
     Insect
    -0.62
     Inher
    -0.60
    enges
    -0.59
     administ
    -0.58
    enge
    -0.57
     Invaders
    -0.55
     Summer
    -0.55
     Influence
    -0.54
     Belg
    -0.54
    POSITIVE LOGITS
     0
    0.79
    3
    0.74
    0
    0.74
    7
    0.73
     TBA
    0.73
     7
    0.69
    4
    0.69
     3
    0.68
    5
    0.67
    9
    0.67
    Activations Density 0.095%

    No Known Activations