© 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. 8564
    Prev
    Next
    INDEX
    Explanations

    software version numbers

    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
    601
    +0.14
    0.6%
    24
    +0.11
    0.5%
    436
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.03
    693
    +0.11
    0.03
    388
    +0.10
    0.02
    Negative Logits
    ierrez
    -0.71
    çĶ°
    -0.70
     needle
    -0.67
    directed
    -0.66
     angles
    -0.66
    isphere
    -0.66
     Nanto
    -0.65
     aisle
    -0.65
     outlet
    -0.64
     motel
    -0.64
    POSITIVE LOGITS
    beta
    1.09
    Version
    1.00
    xx
    0.89
     Version
    0.86
     beta
    0.83
     Update
    0.81
    Beta
    0.80
    +,
    0.80
     SDK
    0.80
     upgr
    0.78
    Activations Density 0.059%

    No Known Activations