© 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. 2206
    Prev
    Next
    INDEX
    Explanations

    emotional or impactful adjectives and their intensities

    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
    362
    +0.13
    0.6%
    572
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.13
    0.06
    362
    +0.11
    0.06
    408
    +0.11
    0.06
    Negative Logits
    ernels
    -0.99
    ometers
    -0.90
    hops
    -0.85
    iths
    -0.85
    Ingredients
    -0.84
    types
    -0.83
    models
    -0.83
    groups
    -0.83
    ptions
    -0.83
    units
    -0.83
    POSITIVE LOGITS
     outburst
    1.14
     breakup
    1.12
     outing
    1.09
     altercation
    1.09
     comeback
    1.08
     outbreak
    1.08
     showdown
    1.07
     flurry
    1.06
     handshake
    1.06
     eruption
    1.05
    Activations Density 0.229%

    No Known Activations