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. 589
    Prev
    Next
    INDEX
    Explanations

    the verb to ‘be’ at the beginning of a sentence

    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
    102
    +0.11
    0.5%
    418
    +0.09
    0.4%
    16
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.11
    0.05
    55
    +0.09
    0.05
    418
    +0.09
    0.04
    Negative Logits
     residue
    -0.66
     orbit
    -0.64
     Ples
    -0.63
     glide
    -0.62
    sonian
    -0.62
     hops
    -0.60
     hoops
    -0.59
    pick
    -0.58
     Selection
    -0.57
     Comet
    -0.57
    POSITIVE LOGITS
    hemoth
    1.38
    heading
    1.25
    yond
    1.24
    arers
    1.20
    ijing
    1.18
    ardless
    1.15
    acons
    1.14
    ige
    1.06
    auc
    1.05
    getting
    1.05
    Activations Density 0.266%

    No Known Activations