© 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 12288
    9. 8-RES_FS12288-JB
    11. 10597
    Prev
    Next
    INDEX
    Explanations

    phrases related to news report topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    451
    +0.12
    0.5%
    146
    +0.11
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.05
    403
    +0.11
    0.03
    362
    +0.11
    0.04
    Negative Logits
    yy
    -0.70
     GPA
    -0.60
    arat
    -0.59
     ppm
    -0.58
     nephew
    -0.58
     uncond
    -0.57
     subscribing
    -0.57
    ct
    -0.56
    hes
    -0.56
    lean
    -0.56
    POSITIVE LOGITS
     ridicule
    1.09
     ire
    1.03
    ENTION
    0.96
     scorn
    0.96
     attention
    0.89
     controversy
    0.82
     contention
    0.82
    spection
    0.80
     scrutiny
    0.77
     criticism
    0.76
    Activations Density 0.223%

    No Known Activations