© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong opinions or criticisms

    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
    +0.21
    1.0%
    362
    +0.15
    0.7%
    393
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.11
    385
    +0.15
    0.10
    608
    +0.15
    0.09
    Negative Logits
    ounces
    -0.76
    thood
    -0.73
    Ò
    -0.72
    contained
    -0.72
    perse
    -0.70
     âĢº
    -0.67
     overseen
    -0.67
    imi
    -0.66
     resembling
    -0.66
     Includes
    -0.65
    POSITIVE LOGITS
    oret
    1.65
    resa
    1.34
     downside
    1.29
     easiest
    1.22
     reason
    1.21
     irony
    1.20
     biggest
    1.19
    ories
    1.18
     simplest
    1.18
     implication
    1.15
    Activations Density 0.450%

    No Known Activations