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 1536
    5. 8-RES_FS1536-JB
    6. 755
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases or opinions marked by the word 'such' or 'such a'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    421
    +0.10
    0.4%
    655
    +0.09
    0.4%
    203
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    733
    +0.10
    0.04
    622
    +0.09
    0.04
    421
    +0.09
    0.05
    Negative Logits
    ellen
    -0.74
    oil
    -0.73
     Murd
    -0.73
    ntil
    -0.71
    uay
    -0.71
     Polo
    -0.69
    ysc
    -0.67
    emale
    -0.67
    inka
    -0.66
    kick
    -0.65
    POSITIVE LOGITS
    ties
    0.96
    ities
    0.91
     mundane
    0.71
     minded
    0.70
     matters
    0.70
     phenomena
    0.67
     gems
    0.66
     considerations
    0.66
    complex
    0.66
     drastic
    0.66
    Activations Density 1.077%

    No Known Activations