© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3076
    Prev
    Next
    INDEX
    Explanations

    references to characters, factions, or actions in a fictional narrative

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.17
    0.7%
    481
    +0.12
    0.5%
    560
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.06
    659
    +0.12
    0.05
    574
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -1.04
    è¯
    -0.77
     pricing
    -0.75
     fairness
    -0.74
     affordability
    -0.74
     profiling
    -0.74
     polling
    -0.74
     parity
    -0.71
    theless
    -0.70
     billing
    -0.69
    POSITIVE LOGITS
    ords
    1.06
    lords
    1.05
    igers
    1.05
    ians
    1.04
    orians
    1.02
     Clan
    1.01
    onian
    1.00
    hai
    0.99
    arians
    0.99
    rians
    0.98
    Activations Density 0.258%

    No Known Activations