© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18411
    Prev
    Next
    INDEX
    Explanations

    technical terms related to fault tolerance and repair services

    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
    285
    +0.16
    0.7%
    151
    +0.10
    0.5%
    141
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.16
    0.01
    431
    +0.10
    0.01
    151
    +0.10
    0.01
    Negative Logits
    atos
    -0.82
    ISTER
    -0.81
    xon
    -0.73
    CHO
    -0.72
    chedel
    -0.70
    het
    -0.69
    eston
    -0.68
    velop
    -0.67
     livest
    -0.66
    aco
    -0.66
    POSITIVE LOGITS
    lessly
    1.19
    ously
    0.96
    lessness
    0.84
     fault
    0.79
    less
    0.77
     faults
    0.77
    worthiness
    0.74
     forgiven
    0.73
     Fault
    0.73
    士
    0.70
    Activations Density 0.017%

    No Known Activations