© 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 24576
    9. 8-RES_FS24576-JB
    11. 1452
    Prev
    Next
    INDEX
    Explanations

    information related to financial struggles and socioeconomic backgrounds

    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
    732
    +0.12
    0.5%
    121
    +0.10
    0.5%
    468
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.07
    351
    +0.10
    0.04
    646
    +0.10
    0.04
    Negative Logits
    CVE
    -0.98
     Kislyak
    -0.84
    canon
    -0.84
     Cthulhu
    -0.83
    RFC
    -0.80
     Canaver
    -0.78
     spoof
    -0.76
    Leaks
    -0.72
    metry
    -0.71
    Bot
    -0.69
    POSITIVE LOGITS
     paycheck
    1.43
     incomes
    1.42
     income
    1.39
     subsistence
    1.29
     pensions
    1.25
     poverty
    1.25
     wages
    1.24
     pension
    1.20
     groceries
    1.17
     unemployment
    1.17
    Activations Density 0.684%

    No Known Activations