© 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. 10064
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive determiners

    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
    362
    +0.12
    0.5%
    92
    +0.11
    0.5%
    15
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.07
    92
    +0.11
    0.05
    15
    +0.11
    0.05
    Negative Logits
    hots
    -0.86
    leans
    -0.86
    wic
    -0.84
    onyms
    -0.78
    hess
    -0.76
    roup
    -0.73
    atable
    -0.73
    adobe
    -0.72
    phans
    -0.72
    ocument
    -0.72
    POSITIVE LOGITS
     own
    1.37
     psyche
    1.30
     ability
    1.28
     credibility
    1.24
     reputation
    1.19
     worldview
    1.19
     perception
    1.17
     appetite
    1.13
     grasp
    1.10
     livelihood
    1.10
    Activations Density 0.199%

    No Known Activations