© 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. 6935
    Prev
    Next
    INDEX
    Explanations

    words related to economic concepts and technical details regarding policies or projects

    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
    373
    +0.14
    0.7%
    637
    +0.10
    0.5%
    357
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.03
    373
    +0.10
    -0.01
    701
    +0.09
    0.02
    Negative Logits
    é¾
    -0.77
    姫
    -0.71
    IZE
    -0.66
     srfAttach
    -0.64
    Magikarp
    -0.63
    WARE
    -0.62
     drill
    -0.62
     rigging
    -0.61
    CRIP
    -0.60
    DERR
    -0.60
    POSITIVE LOGITS
    yssey
    0.91
    ule
    0.78
    uta
    0.77
    rian
    0.77
    nan
    0.76
    nes
    0.74
    combe
    0.72
    bert
    0.71
    rahim
    0.71
    unia
    0.69
    Activations Density 0.061%

    No Known Activations