© 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 3072
    9. 8-RES_FS3072-JB
    11. 140
    Prev
    Next
    INDEX
    Explanations

    business-related terms, especially relating to technology and investments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    87
    +0.23
    1.1%
    459
    +0.19
    0.9%
    756
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.23
    -0.05
    87
    +0.19
    -0.07
    459
    +0.18
    0.13
    Negative Logits
    shit
    -0.77
     torture
    -0.77
    toggle
    -0.76
     crap
    -0.76
     stupid
    -0.73
    killers
    -0.73
    Anyway
    -0.72
     grop
    -0.70
     pretended
    -0.69
     raping
    -0.69
    POSITIVE LOGITS
     leveraging
    1.06
     partnering
    1.06
     synerg
    1.05
     innovative
    1.04
     initiatives
    0.96
     collaborating
    0.96
     collaborative
    0.96
     integrating
    0.94
     collaborations
    0.94
     partnerships
    0.93
    Activations Density 5.511%

    No Known Activations