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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11735
    Prev
    Next
    INDEX
    Explanations

    accounts of physical altercations and encounters with law enforcement

    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
    430
    +0.13
    0.6%
    640
    +0.13
    0.6%
    6
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.12
    430
    +0.13
    0.10
    255
    +0.12
    0.09
    Negative Logits
    omics
    -1.03
     flagship
    -0.94
     global
    -0.88
     innov
    -0.88
     niche
    -0.87
     synerg
    -0.85
     talent
    -0.83
     planetary
    -0.83
     ambitious
    -0.82
     synergy
    -0.81
    POSITIVE LOGITS
     Then
    1.35
     Afterwards
    1.34
     Later
    1.23
     Luckily
    1.21
     Investigators
    1.19
     Eventually
    1.17
     Witnesses
    1.13
     Authorities
    1.12
    Then
    1.12
     Prosecutors
    1.11
    Activations Density 0.424%

    No Known Activations