© 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. 9786
    Prev
    Next
    INDEX
    Explanations

    words related to enthusiasm or passion

    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
    99
    +0.14
    0.7%
    86
    +0.10
    0.5%
    71
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.14
    0.02
    151
    +0.10
    0.02
    579
    +0.10
    0.02
    Negative Logits
    finding
    -0.81
    busters
    -0.80
    ©¶æ
    -0.78
    adr
    -0.74
    rooms
    -0.68
    wan
    -0.68
    fish
    -0.68
    inates
    -0.67
    nah
    -0.66
    later
    -0.65
    POSITIVE LOGITS
     applause
    0.99
     enthusiastic
    0.89
     enthusiasm
    0.87
     passionate
    0.81
     endorsement
    0.77
     cheering
    0.76
     encour
    0.76
     enough
    0.74
     laughter
    0.73
     embrace
    0.73
    Activations Density 0.047%

    No Known Activations