© 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. 11897
    Prev
    Next
    INDEX
    Explanations

    famous places or events related to countries

    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
    430
    +0.13
    0.6%
    668
    +0.11
    0.5%
    764
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.13
    0.02
    733
    +0.11
    0.01
    111
    +0.11
    0.02
    Negative Logits
    orc
    -0.86
    hon
    -0.84
    phen
    -0.83
    cot
    -0.82
    are
    -0.82
    lon
    -0.80
    atl
    -0.79
    bre
    -0.79
    elf
    -0.77
    nai
    -0.77
    POSITIVE LOGITS
     Images
    1.15
     Album
    0.94
    UTERS
    0.92
     Caption
    0.92
     Pool
    0.87
     Photos
    0.85
     Journals
    0.84
     Gallery
    0.84
     Citation
    0.84
     Photo
    0.82
    Activations Density 0.051%

    No Known Activations