© 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 24576
    9. 8-RES_FS24576-JB
    11. 22732
    Prev
    Next
    INDEX
    Explanations

    adverbs that indicate frequency or manner

    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
    480
    +0.29
    1.4%
    447
    +0.28
    1.4%
    481
    +0.19
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.29
    0.04
    101
    +0.28
    0.05
    480
    +0.19
    0.01
    Negative Logits
     Seym
    -0.81
     Azerb
    -0.60
    istani
    -0.60
    ollar
    -0.58
     Niet
    -0.56
     paramilitary
    -0.56
    bledon
    -0.56
     Coke
    -0.55
     Vaugh
    -0.54
    Nation
    -0.54
    POSITIVE LOGITS
     refers
    0.63
    malink
    0.63
     Released
    0.63
    =>
    0.61
     ];
    0.61
     ]
    0.60
    poses
    0.59
    iverse
    0.59
     Adds
    0.59
     Asked
    0.59
    Activations Density 0.157%

    No Known Activations