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 24576
    5. 8-RES_FS24576-JB
    6. 11768
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, and legal considerations

    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
    580
    +0.10
    0.5%
    756
    +0.10
    0.5%
    134
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.10
    0.07
    55
    +0.10
    0.06
    512
    +0.10
    0.04
    Negative Logits
    aft
    -0.69
     helm
    -0.65
    oppers
    -0.64
    anu
    -0.63
    isy
    -0.63
    shore
    -0.62
    uve
    -0.61
    iator
    -0.61
     fishes
    -0.60
    ft
    -0.60
    POSITIVE LOGITS
     actually
    1.03
     probably
    0.95
     priceless
    0.87
     definitely
    0.86
     nothing
    0.86
     indistinguishable
    0.85
     exactly
    0.84
     indeed
    0.84
     identical
    0.83
     undoubtedly
    0.81
    Activations Density 0.302%

    No Known Activations