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 49152
    5. 8-RES_FS49152-JB
    6. 43165
    Prev
    Next
    INDEX
    Explanations

    references to systems or processes in the context of technology or policy updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.32
    1.5%
    598
    +0.09
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.32
    0.04
    149
    +0.09
    0.03
    739
    +0.09
    0.02
    Negative Logits
    $$$$
    -0.88
     inflic
    -0.65
    ulent
    -0.64
     Amen
    -0.62
    xit
    -0.62
     degrade
    -0.59
     negoti
    -0.59
    exit
    -0.58
    rolet
    -0.58
    æ©
    -0.58
    POSITIVE LOGITS
    fortunately
    0.90
     unfortunately
    0.87
     admittedly
    0.85
     understandably
    0.80
     gist
    0.80
     frankly
    0.76
     blog
    0.75
     hopefully
    0.75
     lately
    0.74
     topic
    0.73
    Activations Density 0.470%

    No Known Activations