© 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. 11832
    Prev
    Next
    INDEX
    Explanations

    words related to propaganda and opinion-sharing

    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
    373
    +0.13
    0.6%
    1
    +0.13
    0.6%
    170
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.13
    0.03
    1
    +0.13
    0.03
    112
    +0.11
    0.03
    Negative Logits
    reat
    -0.68
    ritic
    -0.66
    yip
    -0.64
    knife
    -0.62
    pperc
    -0.62
    atro
    -0.62
    atches
    -0.62
    thren
    -0.60
    FH
    -0.60
    rients
    -0.58
    POSITIVE LOGITS
    ocating
    1.03
    uding
    1.02
    usion
    0.95
    uring
    0.94
     sorts
    0.90
    ocated
    0.87
     kinds
    0.81
    ocation
    0.81
    usions
    0.80
    owing
    0.79
    Activations Density 0.045%

    No Known Activations