© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45624
    Prev
    Next
    INDEX
    Explanations

    phrases indicating source or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    373
    +0.19
    0.9%
    157
    +0.11
    0.5%
    22
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.19
    0.01
    738
    +0.11
    0.01
    592
    +0.09
    0.01
    Negative Logits
    FontSize
    -0.70
    boxing
    -0.69
    emetery
    -0.69
    ocene
    -0.68
    DIV
    -0.67
    Redd
    -0.67
    pled
    -0.66
    sticks
    -0.65
    ewitness
    -0.64
    hooting
    -0.64
    POSITIVE LOGITS
     {}
    0.72
     Alexandria
    0.70
    ='
    0.68
     Tah
    0.68
     Pastebin
    0.68
     {
    0.65
     whence
    0.64
     Environment
    0.62
    ©¶æ
    0.61
     "@
    0.60
    Activations Density 0.006%

    No Known Activations