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 6144
    5. 8-RES_FS6144-JB
    6. 5373
    Prev
    Next
    INDEX
    Explanations

    terms related to interpersonal relationships and partnerships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    247
    +0.14
    0.6%
    447
    +0.13
    0.6%
    340
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.06
    513
    +0.13
    0.04
    132
    +0.12
    0.04
    Negative Logits
    Dou
    -0.76
    prus
    -0.74
    milo
    -0.70
    mington
    -0.70
    rpm
    -0.70
    printed
    -0.69
    ifted
    -0.67
    ambling
    -0.67
    arde
    -0.67
    markets
    -0.66
    POSITIVE LOGITS
     between
    1.10
     relationship
    1.09
     relationships
    1.05
    hips
    1.05
     relations
    0.92
     Between
    0.88
    SHIP
    0.85
     partner
    0.85
    ually
    0.84
    ability
    0.84
    Activations Density 0.373%

    No Known Activations