© 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 1536
    9. 8-RES_FS1536-JB
    11. 1100
    Prev
    Next
    INDEX
    Explanations

    terms related to the military and security, focusing on soldiers, troops, and engineers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.17
    0.8%
    330
    +0.12
    0.5%
    575
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.17
    0.17
    330
    +0.12
    0.16
    537
    +0.11
    0.17
    Negative Logits
    ASED
    -0.63
    OLOG
    -0.61
    FLAG
    -0.59
    Prosecut
    -0.58
    Spl
    -0.58
    yss
    -0.58
     domain
    -0.58
    clusive
    -0.58
    Transaction
    -0.57
    rawdownloadcloneembedreportprint
    -0.57
    POSITIVE LOGITS
    hip
    1.61
    hips
    1.61
    paces
    1.41
     who
    1.29
    ervatives
    1.25
    '
    1.22
    folk
    1.15
     alike
    1.11
    pace
    1.08
    mith
    1.08
    Activations Density 2.466%

    No Known Activations