© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or phrases

    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
    314
    +0.19
    0.9%
    264
    +0.10
    0.5%
    698
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.19
    0.07
    314
    +0.10
    0.03
    537
    +0.10
    0.06
    Negative Logits
     interval
    -0.70
     Collins
    -0.67
     opin
    -0.66
     MEN
    -0.65
     Norris
    -0.65
     entert
    -0.64
     increments
    -0.64
     intervals
    -0.64
     Meadows
    -0.64
     sacrific
    -0.64
    POSITIVE LOGITS
    esque
    1.73
    style
    1.71
    themed
    1.70
    inspired
    1.69
    like
    1.52
    derived
    1.52
    based
    1.49
    centric
    1.47
    induced
    1.46
    related
    1.45
    Activations Density 0.137%

    No Known Activations