© 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. 9619
    Prev
    Next
    INDEX
    Explanations

    words related to political conflict and international relations

    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
    36
    +0.23
    1.1%
    297
    +0.12
    0.6%
    538
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.23
    0.07
    250
    +0.12
    0.03
    538
    +0.11
    0.03
    Negative Logits
    lees
    -0.74
    projects
    -0.63
    ographs
    -0.62
    cv
    -0.61
    attacks
    -0.59
    Catal
    -0.59
    uploads
    -0.59
     assemblies
    -0.58
    UTC
    -0.58
    values
    -0.58
    POSITIVE LOGITS
     handful
    1.36
     few
    1.24
     fraction
    1.18
     couple
    1.09
    few
    1.07
     glimpse
    0.99
     dozen
    0.98
     fleeting
    0.93
     hint
    0.93
     glance
    0.92
    Activations Density 0.097%

    No Known Activations