© 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. 44
    Prev
    Next
    INDEX
    Explanations

    information about non-profit organizations and their missions

    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
    679
    +0.13
    0.6%
    723
    +0.13
    0.6%
    295
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.13
    0.14
    498
    +0.13
    0.10
    723
    +0.12
    0.09
    Negative Logits
     impat
    -0.80
    grain
    -0.75
     strokes
    -0.69
     comprehension
    -0.68
     pardon
    -0.67
     inconvenience
    -0.67
     stare
    -0.66
     calculus
    -0.66
     spoil
    -0.66
     precipitation
    -0.66
    POSITIVE LOGITS
     headquartered
    1.40
     disbanded
    1.24
     sponsoring
    1.21
     founded
    1.15
     staffed
    1.14
     operated
    1.14
     operates
    1.12
     partnered
    1.12
     affiliated
    1.11
     subsidiaries
    1.08
    Activations Density 3.083%

    No Known Activations