© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions such as amazement, indignation, disappointment, sadness, anger, and frustration

    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
    +0.14
    0.6%
    288
    +0.13
    0.6%
    86
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.14
    0.04
    51
    +0.13
    0.04
    288
    +0.12
    0.05
    Negative Logits
    amins
    -0.83
    ĻĤ
    -0.78
    eor
    -0.63
     Conduct
    -0.63
     rough
    -0.60
    nesium
    -0.60
    xon
    -0.60
    asus
    -0.60
     Blueprint
    -0.60
    opsis
    -0.59
    POSITIVE LOGITS
    lessness
    1.01
    fulness
    0.97
     stricken
    0.92
     overcame
    0.89
     stemming
    0.88
     awaiting
    0.88
    ingly
    0.86
     arising
    0.84
     aroused
    0.81
    ously
    0.80
    Activations Density 0.134%

    No Known Activations