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. 267
    Prev
    Next
    INDEX
    Explanations

    data related to statistics, rankings, and numerical values across various categories

    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
    699
    +0.12
    0.5%
    574
    +0.11
    0.5%
    391
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.12
    0.02
    616
    +0.11
    0.08
    184
    +0.10
    0.04
    Negative Logits
    ĪĴ
    -0.74
    hement
    -0.73
    ©¶æ
    -0.69
    çīĪ
    -0.68
    pecially
    -0.68
    rog
    -0.67
    nik
    -0.67
    western
    -0.66
    chool
    -0.64
    haven
    -0.64
    POSITIVE LOGITS
     total
    1.28
     percentage
    1.28
     allowable
    1.22
     number
    1.21
     amount
    1.20
     calories
    1.19
     mileage
    1.18
     GDP
    1.15
     throughput
    1.14
     value
    1.10
    Activations Density 2.995%

    No Known Activations