© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    financial and economic 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
    225
    +0.12
    0.5%
    496
    +0.10
    0.5%
    191
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    444
    +0.10
    0.05
    35
    +0.09
    0.05
    Negative Logits
     Oval
    -0.69
    ENDED
    -0.67
     Moody
    -0.67
     Nieto
    -0.64
     Width
    -0.64
    dq
    -0.63
     Gemini
    -0.63
     Dresden
    -0.61
     Summit
    -0.60
     Briggs
    -0.59
    POSITIVE LOGITS
    payer
    0.86
     reward
    0.82
     bribes
    0.81
     Donation
    0.81
     rewards
    0.80
     robbery
    0.79
     money
    0.79
     sponsorship
    0.79
     donated
    0.78
     prizes
    0.76
    Activations Density 0.301%

    No Known Activations