© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    words related to financial matters or tax exemptions

    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
    288
    +0.14
    0.6%
    447
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    427
    +0.14
    0.01
    288
    +0.11
    0.01
    222
    +0.11
    0.01
    Negative Logits
     Zeit
    -0.80
    ãĥ¥
    -0.78
     Carly
    -0.65
     Roses
    -0.65
     Xiang
    -0.63
    KR
    -0.63
    aces
    -0.61
     Bras
    -0.60
    yard
    -0.60
     Toast
    -0.59
    POSITIVE LOGITS
     exemptions
    1.15
     exemption
    1.11
     exempt
    1.06
    exempt
    0.96
     exempted
    0.94
     afforded
    0.89
    emption
    0.88
     immunity
    0.86
    untarily
    0.85
    icut
    0.83
    Activations Density 0.023%

    No Known Activations