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 3072
    5. 8-RES_FS3072-JB
    6. 1937
    Prev
    Next
    INDEX
    Explanations

    words related to actions and events in a narrative

    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
    55
    +0.13
    0.6%
    418
    +0.12
    0.6%
    7
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.13
    0.16
    102
    +0.12
    0.15
    418
    +0.12
    0.11
    Negative Logits
    inventoryQuantity
    -0.64
     resear
    -0.61
     Dragonbound
    -0.59
     pains
    -0.59
     dislike
    -0.58
     Response
    -0.58
     Ago
    -0.57
     rant
    -0.56
     Anger
    -0.55
     Mot
    -0.55
    POSITIVE LOGITS
     available
    1.05
     forthcoming
    0.99
     thrown
    0.95
     exchanged
    0.91
     flown
    0.90
     abound
    0.89
     substituted
    0.89
     drawn
    0.88
     taken
    0.88
     introduced
    0.87
    Activations Density 1.507%

    No Known Activations