© 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 3072
    9. 8-RES_FS3072-JB
    11. 1031
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    551
    +0.14
    0.7%
    139
    +0.13
    0.6%
    597
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.14
    0.11
    551
    +0.13
    0.11
    718
    +0.10
    0.10
    Negative Logits
     Gothic
    -0.77
    aic
    -0.69
     consequential
    -0.66
     Window
    -0.65
     Conversation
    -0.63
     Meaning
    -0.63
     Azerbai
    -0.63
     Organizations
    -0.61
     Palest
    -0.59
     Warden
    -0.59
    POSITIVE LOGITS
     took
    1.23
     knew
    1.17
     gave
    1.17
     drove
    1.15
     went
    1.15
     underwent
    1.14
     blew
    1.13
     stole
    1.11
     became
    1.11
     chose
    1.10
    Activations Density 1.036%

    No Known Activations