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 6144
    5. 8-RES_FS6144-JB
    6. 5416
    Prev
    Next
    INDEX
    Explanations

    instances involving web links and technical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    326
    +0.12
    0.5%
    488
    +0.10
    0.5%
    104
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    488
    +0.10
    0.05
    6
    +0.10
    0.05
    Negative Logits
     millenn
    -0.82
    anooga
    -0.74
     nomine
    -0.70
     cycling
    -0.67
     suprem
    -0.65
     mutual
    -0.64
    neys
    -0.64
    ĸļ
    -0.63
     masc
    -0.63
     historians
    -0.62
    POSITIVE LOGITS
     partName
    1.12
    806
    1.10
    641
    1.06
    708
    1.05
    807
    1.05
    608
    1.04
    758
    1.04
    336
    1.04
    646
    1.04
    756
    1.03
    Activations Density 0.148%

    No Known Activations