Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19039
    Prev
    Next
    INDEX
    Explanations

    phrases related to falling or being in love

    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
    568
    +0.13
    0.6%
    591
    +0.11
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.13
    0.04
    665
    +0.11
    0.05
    641
    +0.10
    0.04
    Negative Logits
     postponed
    -0.69
     maintenance
    -0.67
     veto
    -0.67
     backups
    -0.66
    abouts
    -0.65
     disbanded
    -0.63
     roundup
    -0.63
    oret
    -0.63
     HDD
    -0.61
     setbacks
    -0.61
    POSITIVE LOGITS
    Sense
    0.89
    illusion
    0.80
    OOD
    0.80
     instinctively
    0.80
    paralle
    0.80
     anew
    0.78
     Indigo
    0.78
    ench
    0.78
    iasm
    0.78
     scent
    0.77
    Activations Density 0.265%

    No Known Activations