© 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. 19369
    Prev
    Next
    INDEX
    Explanations

    phrases related to happiness or positive feelings

    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
    195
    +0.10
    0.4%
    759
    +0.10
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.01
    493
    +0.10
    0.01
    565
    +0.09
    0.01
    Negative Logits
     guiActiveUn
    -0.63
     Kuwait
    -0.61
     fixation
    -0.60
    trl
    -0.60
    senal
    -0.59
     Divinity
    -0.58
     VIDEOS
    -0.58
     Nile
    -0.57
     Schiff
    -0.57
     Engineers
    -0.57
    POSITIVE LOGITS
    ened
    1.23
    ily
    1.17
    ening
    1.13
    iest
    1.13
    iness
    1.12
    ings
    0.95
    earance
    0.94
    ert
    0.94
    erc
    0.93
    ier
    0.90
    Activations Density 0.020%

    No Known Activations