© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7819
    Prev
    Next
    INDEX
    Explanations

    words related to activism and protests in political contexts

    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
    +0.22
    1.0%
    481
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.22
    0.03
    224
    +0.13
    0.03
    86
    +0.12
    0.02
    Negative Logits
    Transaction
    -0.72
    BuyableInstoreAndOnline
    -0.71
    uncture
    -0.70
    lasses
    -0.68
    Sales
    -0.68
    bit
    -0.67
    ournal
    -0.66
     Tycoon
    -0.66
    Sense
    -0.65
    HAHA
    -0.65
    POSITIVE LOGITS
     chanting
    1.15
     protesting
    1.00
     marched
    1.00
     encamp
    0.98
     protestors
    0.98
     chanted
    0.97
     protesters
    0.95
     demonstrators
    0.92
     peacefully
    0.89
     besie
    0.88
    Activations Density 0.051%

    No Known Activations