© 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. 22005
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial or economic topics, particularly focusing on the concept of excess

    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
    289
    +0.12
    0.5%
    271
    +0.11
    0.5%
    647
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    763
    +0.11
    0.01
    738
    +0.11
    0.01
    Negative Logits
    Äĩ
    -0.72
    ©¶æ
    -0.70
    ramid
    -0.70
    udder
    -0.68
    ŃĶ
    -0.66
    hran
    -0.64
    mberg
    -0.64
    stal
    -0.64
    morrow
    -0.63
    jah
    -0.63
    POSITIVE LOGITS
    ively
    1.00
    iveness
    0.94
    es
    0.94
     amounts
    0.92
     baggage
    0.90
     capacity
    0.88
     quantities
    0.86
     quantity
    0.82
    ibilities
    0.78
     moisture
    0.76
    Activations Density 0.026%

    No Known Activations