© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    phrases related to political organizations and controversial topics

    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
    314
    +0.13
    0.6%
    218
    +0.10
    0.4%
    100
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.04
    647
    +0.10
    0.03
    134
    +0.09
    0.03
    Negative Logits
     tales
    -0.87
     frustrations
    -0.78
    scenes
    -0.76
     anecdotes
    -0.73
    ebus
    -0.71
     juxtap
    -0.70
    ramids
    -0.69
     whispers
    -0.69
     leaps
    -0.66
     reminis
    -0.66
    POSITIVE LOGITS
    eligible
    1.09
     ineligible
    1.08
     eligible
    1.03
     unfit
    1.02
     punishable
    0.95
    angered
    0.95
     exempt
    0.93
    ocide
    0.86
     unlawful
    0.86
     Category
    0.84
    Activations Density 0.267%

    No Known Activations