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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9693
    Prev
    Next
    INDEX
    Explanations

    words related to empathy or sympathy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    161
    +0.13
    0.6%
    288
    +0.11
    0.5%
    0
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    161
    +0.11
    0.02
    317
    +0.10
    0.03
    Negative Logits
    kj
    -0.79
    ouver
    -0.78
    aer
    -0.73
    corn
    -0.72
    growth
    -0.71
    bris
    -0.67
    heimer
    -0.66
    arde
    -0.66
    down
    -0.62
    teen
    -0.62
    POSITIVE LOGITS
     towards
    0.90
     toward
    0.85
    athetic
    0.83
    arity
    0.83
     gesture
    0.81
     sympathy
    0.81
    ately
    0.73
    itism
    0.72
     solidarity
    0.72
    ISM
    0.72
    Activations Density 0.111%

    No Known Activations