© 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. 25746
    Prev
    Next
    INDEX
    Explanations

    references to mercury

    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%
    385
    +0.13
    0.6%
    418
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.01
    556
    +0.13
    0.01
    548
    +0.11
    0.00
    Negative Logits
    76561
    -0.94
    mble
    -0.90
    ========
    -0.77
    stretched
    -0.74
    ESCO
    -0.70
    erness
    -0.69
    REDACTED
    -0.69
    hani
    -0.68
    ements
    -0.68
    herer
    -0.68
    POSITIVE LOGITS
     Mercury
    0.84
    ials
    0.69
     rays
    0.69
    ury
    0.68
    enary
    0.67
    ial
    0.67
     Mars
    0.67
    bach
    0.66
     iod
    0.66
     Seal
    0.65
    Activations Density 0.005%

    No Known Activations