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. 609
    Prev
    Next
    INDEX
    Explanations

    technological and urban development terms, particularly related to smart cities and transportation

    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
    7
    +0.11
    0.5%
    368
    +0.10
    0.4%
    594
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.11
    0.10
    102
    +0.10
    0.13
    512
    +0.09
    0.08
    Negative Logits
     Pension
    -0.69
    DoS
    -0.64
     Tours
    -0.62
     successors
    -0.61
    ardy
    -0.60
    ivan
    -0.60
    ONDON
    -0.60
     Yok
    -0.59
    Syrian
    -0.58
    Write
    -0.58
    POSITIVE LOGITS
     everywhere
    1.07
     synonymous
    1.01
     inherently
    1.01
     intrinsically
    0.96
     traditionally
    0.95
     rife
    0.94
     scarce
    0.92
     ubiquitous
    0.91
     plentiful
    0.91
     prevalent
    0.90
    Activations Density 2.448%

    No Known Activations