© 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 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. 37485
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or names associated with the Yukon region

    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
    496
    +0.12
    0.6%
    537
    +0.11
    0.5%
    744
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    232
    +0.11
    0.01
    284
    +0.11
    0.01
    Negative Logits
    AMS
    -0.74
     Haas
    -0.73
    ORY
    -0.65
    urally
    -0.64
    BALL
    -0.63
    Football
    -0.61
     eject
    -0.58
    milo
    -0.57
    ATURES
    -0.57
     pestic
    -0.57
    POSITIVE LOGITS
    imura
    1.15
    uki
    0.98
    imoto
    0.90
    oshi
    0.87
    jin
    0.87
     Yuk
    0.83
    hiro
    0.82
    imet
    0.81
    wu
    0.79
    aku
    0.79
    Activations Density 0.010%

    No Known Activations