© 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. 18761
    Prev
    Next
    INDEX
    Explanations

    words related to conflicts or troubles

    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
    481
    +0.16
    0.8%
    689
    +0.12
    0.6%
    396
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.16
    0.05
    396
    +0.12
    0.04
    45
    +0.12
    0.03
    Negative Logits
    pta
    -0.92
    ortmund
    -0.87
    olphins
    -0.86
    atari
    -0.86
    regation
    -0.85
    iets
    -0.84
    OND
    -0.83
    ULE
    -0.82
    kamp
    -0.80
    udence
    -0.79
    POSITIVE LOGITS
     downright
    1.30
     prone
    1.21
     lacking
    1.16
     incapable
    1.14
     indistinguishable
    1.12
     riddled
    1.10
     aest
    1.09
     resistant
    1.07
     devoid
    1.06
     capable
    1.05
    Activations Density 0.324%

    No Known Activations