© 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. 7012
    Prev
    Next
    INDEX
    Explanations

    political and economic terms and concepts, as well as mentions of societal issues and roles

    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
    393
    +0.11
    0.5%
    645
    +0.11
    0.5%
    363
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.11
    0.06
    120
    +0.11
    0.06
    384
    +0.11
    0.05
    Negative Logits
    added
    -0.71
    jah
    -0.70
    +.
    -0.68
    PLE
    -0.67
     Recomm
    -0.66
    FREE
    -0.65
    java
    -0.64
    KEN
    -0.64
    vec
    -0.63
    requires
    -0.62
    POSITIVE LOGITS
     others
    0.85
    rogen
    0.83
    rogens
    0.81
     other
    0.77
     consequently
    0.75
     subsequent
    0.72
     surrog
    0.70
     allied
    0.69
     livelihood
    0.69
     commentators
    0.68
    Activations Density 0.217%

    No Known Activations