© 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. 18562
    Prev
    Next
    INDEX
    Explanations

    references to military service and personnel

    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
    344
    +0.14
    0.6%
    314
    +0.13
    0.6%
    566
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.14
    0.08
    552
    +0.13
    0.07
    566
    +0.12
    0.07
    Negative Logits
    âĻ¦
    -0.65
    PI
    -0.64
    etting
    -0.60
     anymore
    -0.60
    bie
    -0.58
    hack
    -0.57
    orph
    -0.56
    owe
    -0.56
    bery
    -0.56
    VR
    -0.56
    POSITIVE LOGITS
     been
    1.29
     undergone
    1.14
     begun
    1.12
     previously
    1.12
    iths
    1.05
     gone
    1.02
     flown
    1.01
     originally
    1.00
     gotten
    0.99
    been
    0.99
    Activations Density 0.143%

    No Known Activations