© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9334
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic impacts, particularly on employment and prices

    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
    480
    +0.22
    1.0%
    435
    +0.10
    0.5%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.22
    0.08
    608
    +0.10
    0.09
    636
    +0.09
    0.04
    Negative Logits
    inus
    -0.61
     Liter
    -0.61
     ·
    -0.60
    ';
    -0.59
    @#&
    -0.58
     ALWAYS
    -0.57
     Culture
    -0.55
     raged
    -0.54
    sych
    -0.53
    Beaut
    -0.53
    POSITIVE LOGITS
     someday
    1.31
     future
    0.94
     anytime
    0.91
     recons
    0.90
     2020
    0.89
     sooner
    0.89
     next
    0.84
     forthcoming
    0.84
     reconsider
    0.83
     2019
    0.83
    Activations Density 1.142%

    No Known Activations