© 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 49152
    9. 8-RES_FS49152-JB
    11. 41595
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental issues and wildlife conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.38
    1.9%
    470
    +0.10
    0.5%
    652
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.38
    -0.01
    470
    +0.10
    0.03
    390
    +0.09
    0.03
    Negative Logits
     devs
    -0.62
    SPONSORED
    -0.62
    Ability
    -0.59
     somet
    -0.59
    ."[
    -0.57
     thereof
    -0.57
    ](
    -0.57
     [...]
    -0.57
    âĢ¦]
    -0.56
    catentry
    -0.56
    POSITIVE LOGITS
     controvers
    0.77
     famously
    0.73
    quartered
    0.71
     notoriously
    0.70
     fiercely
    0.67
     plagued
    0.67
     criticised
    0.64
     embroiled
    0.62
     dogged
    0.62
     accused
    0.61
    Activations Density 0.861%

    No Known Activations