© 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 EvalsExportsinterp-engineNEWAPI 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. 24517
    Prev
    Next
    INDEX
    Explanations

    phrases that express intensity or significance of emotions and events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.13
    0.6%
    276
    +0.12
    0.5%
    726
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.04
    724
    +0.12
    0.04
    726
    +0.11
    0.03
    Negative Logits
    ></
    -0.64
     endless
    -0.64
     superiority
    -0.61
    engine
    -0.60
     sufficient
    -0.59
    Begin
    -0.59
    icht
    -0.58
    Complete
    -0.58
     equivalents
    -0.57
     datas
    -0.55
    POSITIVE LOGITS
     because
    0.79
     considering
    0.79
    irtual
    0.73
    imaru
    0.70
    amazon
    0.67
     than
    0.67
    because
    0.66
     since
    0.66
    ebted
    0.65
     insofar
    0.63
    Activations Density 0.137%

    No Known Activations