© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45430
    Prev
    Next
    INDEX
    Explanations

    references to various types of flowers and their characteristics

    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
    288
    +0.13
    0.6%
    140
    +0.09
    0.4%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.13
    0.01
    288
    +0.09
    0.01
    260
    +0.09
    0.01
    Negative Logits
     unden
    -0.74
    gregation
    -0.68
    ilitary
    -0.68
    ulhu
    -0.67
    achine
    -0.66
    ahon
    -0.66
    nesota
    -0.66
    quickShipAvailable
    -0.65
    govern
    -0.65
    */(
    -0.64
    POSITIVE LOGITS
    pots
    0.98
     arranging
    0.97
     buds
    0.96
     bloom
    0.95
     flowers
    0.94
     blo
    0.93
    fruit
    0.91
     bou
    0.91
    mary
    0.90
    flower
    0.88
    Activations Density 0.012%

    No Known Activations