© 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 24576
    9. 8-RES_FS24576-JB
    11. 17428
    Prev
    Next
    INDEX
    Explanations

    information related to rewards, giveaways, contests, and winners in a promotional context

    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
    313
    +0.10
    0.5%
    592
    +0.10
    0.4%
    265
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.10
    0.04
    313
    +0.10
    0.04
    149
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.86
     grounding
    -0.71
    baugh
    -0.71
     displacement
    -0.69
     turbulence
    -0.68
     pastoral
    -0.68
     sluggish
    -0.67
     doctr
    -0.67
    olit
    -0.67
    erguson
    -0.67
    POSITIVE LOGITS
     prizes
    1.15
     Kickstarter
    1.11
     PayPal
    1.10
     prize
    1.09
     Prize
    1.09
     donations
    1.08
     bidder
    1.08
     Reward
    1.07
     Winners
    1.07
     Participant
    1.06
    Activations Density 0.656%

    No Known Activations