© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    information related to economic policies and government legislation

    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
    +0.46
    2.4%
    266
    +0.10
    0.5%
    680
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.46
    0.00
    266
    +0.10
    0.09
    300
    +0.09
    0.06
    Negative Logits
     Tiff
    -0.70
     VIDEOS
    -0.69
    lore
    -0.68
     colourful
    -0.65
     Tales
    -0.63
     Guru
    -0.60
     FANT
    -0.60
     humour
    -0.59
     Sung
    -0.58
     Passion
    -0.58
    POSITIVE LOGITS
     defund
    1.06
     repeal
    1.05
     unilaterally
    1.02
     abol
    0.99
     renegoti
    0.98
     abolish
    0.95
     amnesty
    0.94
     tariffs
    0.94
     veto
    0.92
     legisl
    0.91
    Activations Density 1.127%

    No Known Activations