© 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 12288
    9. 8-RES_FS12288-JB
    11. 10820
    Prev
    Next
    INDEX
    Explanations

    political conflicts between different countries or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    121
    +0.14
    0.6%
    491
    +0.09
    0.4%
    694
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.10
    121
    +0.09
    0.08
    152
    +0.09
    0.08
    Negative Logits
     evolves
    -0.80
    rogram
    -0.79
    sense
    -0.71
     adaptations
    -0.69
    OGR
    -0.69
    olkien
    -0.68
    FU
    -0.68
     wisely
    -0.66
     substit
    -0.66
    ritch
    -0.65
    POSITIVE LOGITS
     premises
    0.88
     nightclub
    0.87
     suspected
    0.85
     buildings
    0.84
     mosque
    0.83
     unarmed
    0.82
    area
    0.80
     gunman
    0.79
     convoy
    0.78
     residential
    0.77
    Activations Density 0.850%

    No Known Activations