© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    definitions or descriptions of terms

    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
    +0.10
    0.5%
    300
    +0.09
    0.4%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.10
    0.03
    692
    +0.09
    0.03
    507
    +0.09
    0.03
    Negative Logits
    ersen
    -0.74
    igham
    -0.70
     showc
    -0.70
    erb
    -0.69
     Tiger
    -0.68
     Hitman
    -0.66
    JM
    -0.66
    Args
    -0.66
     Jagu
    -0.64
     Hulk
    -0.63
    POSITIVE LOGITS
     Definition
    0.91
     encompass
    0.86
     defined
    0.84
     combining
    0.81
     encomp
    0.75
     consist
    0.75
    defined
    0.74
     "âĢ¦
    0.73
     subtract
    0.72
     subjective
    0.71
    Activations Density 0.200%

    No Known Activations