© 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. 9576
    Prev
    Next
    INDEX
    Explanations

    legal and political terms or references

    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
    481
    +0.11
    0.5%
    441
    +0.11
    0.5%
    616
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.11
    0.03
    294
    +0.11
    0.02
    14
    +0.11
    0.02
    Negative Logits
    ©¶æ¥µ
    -0.89
    ront
    -0.80
    omorphic
    -0.80
    stration
    -0.77
    din
    -0.74
    agic
    -0.74
    rio
    -0.73
    senal
    -0.73
    odes
    -0.70
    ics
    -0.70
    POSITIVE LOGITS
     alternatively
    1.01
     thence
    0.98
    -)
    0.98
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.90
     furthermore
    0.90
    theless
    0.84
     moreover
    0.81
     additionally
    0.81
    âĢ¢âĢ¢
    0.80
     yea
    0.79
    Activations Density 0.057%

    No Known Activations