© 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 49152
    9. 8-RES_FS49152-JB
    11. 45845
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning people or sending them home

    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
    481
    +0.25
    1.2%
    447
    +0.18
    0.9%
    685
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.25
    0.05
    469
    +0.18
    0.04
    223
    +0.11
    0.04
    Negative Logits
     eyebrow
    -0.78
     predictive
    -0.68
     streak
    -0.66
     gauge
    -0.64
    ĸļ
    -0.64
     Gamble
    -0.63
     Spotlight
    -0.61
    ggles
    -0.61
     brainstorm
    -0.60
     watt
    -0.60
    POSITIVE LOGITS
     safely
    1.17
     captivity
    1.11
     peacefully
    1.10
     alive
    1.09
     unlawfully
    0.96
     intact
    0.92
     captives
    0.87
     permanently
    0.87
    ylum
    0.86
     voluntarily
    0.85
    Activations Density 0.214%

    No Known Activations