© 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. 22200
    Prev
    Next
    INDEX
    Explanations

    references to figures or individuals in a context implying importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered 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
    549
    +0.12
    0.6%
    129
    +0.11
    0.5%
    276
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.12
    0.02
    383
    +0.11
    0.02
    129
    +0.11
    0.02
    Negative Logits
    ModLoader
    -0.74
    IFE
    -0.72
    velength
    -0.71
    termination
    -0.69
    umenthal
    -0.69
    DAQ
    -0.69
    okemon
    -0.69
    bey
    -0.69
    é¾
    -0.68
    GBT
    -0.68
    POSITIVE LOGITS
     prominently
    1.07
    head
    1.03
     skating
    0.98
    heads
    0.94
    enance
    0.90
    downs
    0.79
     figures
    0.79
    books
    0.79
    book
    0.76
    maker
    0.75
    Activations Density 0.024%

    No Known Activations