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. 26255
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific values related to various subjects

    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
    276
    +0.13
    0.6%
    167
    +0.11
    0.5%
    132
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.02
    310
    +0.11
    0.02
    326
    +0.10
    0.02
    Negative Logits
    ĸļ
    -0.94
    andise
    -0.86
    raints
    -0.80
    akening
    -0.80
    ItemTracker
    -0.79
    ĺħ
    -0.77
    isoft
    -0.75
    atis
    -0.74
    aken
    -0.74
    atchewan
    -0.73
    POSITIVE LOGITS
    nd
    0.99
    00
    0.86
    backer
    0.84
    ijk
    0.84
    LECT
    0.80
    holm
    0.76
    803
    0.73
    FW
    0.72
    VICE
    0.71
    yard
    0.69
    Activations Density 0.025%

    No Known Activations