© 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. 756
    Prev
    Next
    INDEX
    Explanations

    information about events, locations, and descriptions

    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
    430
    +0.14
    0.6%
    603
    +0.11
    0.5%
    158
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.11
    158
    +0.11
    0.08
    384
    +0.10
    0.07
    Negative Logits
    egal
    -0.90
    ript
    -0.88
    onne
    -0.82
    leeve
    -0.80
    ordes
    -0.80
    respons
    -0.79
    ATOR
    -0.79
    onductor
    -0.78
    ategory
    -0.76
    åĬ
    -0.73
    POSITIVE LOGITS
     afternoon
    1.75
     morning
    1.72
     mornings
    1.64
     night
    1.62
     evening
    1.60
     nights
    1.47
     Night
    1.41
     evenings
    1.33
    morning
    1.20
     Morning
    1.16
    Activations Density 0.272%

    No Known Activations