© 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. 1261
    Prev
    Next
    INDEX
    Explanations

    mentions of infrastructure development and related economic activities

    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
    447
    +0.15
    0.7%
    717
    +0.15
    0.7%
    255
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.07
    640
    +0.15
    0.08
    546
    +0.12
    0.04
    Negative Logits
     consolidated
    -0.76
     affili
    -0.76
     portfolio
    -0.76
    ©¶æ¥µ
    -0.71
     Academic
    -0.71
     finalized
    -0.71
     investor
    -0.70
     overarching
    -0.70
    isan
    -0.69
    ainment
    -0.68
    POSITIVE LOGITS
     Shutterstock
    1.06
    literally
    0.91
     nausea
    0.82
     vomit
    0.82
     injure
    0.81
    instead
    0.79
     dehyd
    0.78
     spraying
    0.78
     vomiting
    0.78
     toilets
    0.77
    Activations Density 0.812%

    No Known Activations