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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 46130
    Prev
    Next
    INDEX
    Explanations

    references to dietary advice and health-related topics

    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
    447
    +0.14
    0.6%
    160
    +0.10
    0.4%
    406
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.14
    0.05
    255
    +0.10
    0.05
    679
    +0.09
    0.05
    Negative Logits
    SPONSORED
    -0.82
     guiActiveUnfocused
    -0.73
    fml
    -0.72
    åħī
    -0.69
    ctuary
    -0.69
    ervative
    -0.66
    oho
    -0.65
    çīĪ
    -0.64
    arthed
    -0.64
    eman
    -0.63
    POSITIVE LOGITS
     Especially
    1.01
     Luckily
    0.94
     Fortunately
    0.85
     juggling
    0.84
     sometimes
    0.82
    especially
    0.82
     especially
    0.81
     deadlines
    0.79
     stressful
    0.78
     Thankfully
    0.78
    Activations Density 0.300%

    No Known Activations