© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotional attachment or significance

    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
    252
    +0.12
    0.6%
    459
    +0.09
    0.4%
    413
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.12
    0.03
    13
    +0.09
    0.02
    760
    +0.09
    0.02
    Negative Logits
    hari
    -0.76
     âĶĤ
    -0.60
     Reaction
    -0.59
     background
    -0.55
    available
    -0.55
    DW
    -0.54
    æ©Ł
    -0.54
     CY
    -0.53
     Ze
    -0.53
     Rumble
    -0.53
    POSITIVE LOGITS
    bye
    0.78
    ppa
    0.76
     goodbye
    0.74
    LOS
    0.72
     Goodbye
    0.71
     farewell
    0.68
    roads
    0.67
    ueller
    0.61
    ŃĶ
    0.61
     THANK
    0.61
    Activations Density 0.101%

    No Known Activations