© 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. 8018
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect, specifically focusing on the concept of 'turning'

    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
    316
    +0.10
    0.5%
    128
    +0.09
    0.4%
    655
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.10
    0.01
    324
    +0.09
    0.01
    316
    +0.09
    0.01
    Negative Logits
    alty
    -0.64
    ntax
    -0.63
     Tacoma
    -0.61
     Begin
    -0.61
     Kal
    -0.60
     Lethal
    -0.59
     Challenger
    -0.59
     Tub
    -0.58
     Else
    -0.58
    ilion
    -0.58
    POSITIVE LOGITS
    SPONSORED
    0.86
    udes
    0.73
     incentiv
    0.71
    ãĥł
    0.71
     ACTIONS
    0.70
     contributes
    0.69
    èĥ
    0.68
    demand
    0.67
    catentry
    0.66
    ectar
    0.66
    Activations Density 0.019%

    No Known Activations