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. 23250
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to health impacts and diseases

    oai_token-act-pair · gpt-4o-miniTriggered 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
    496
    +0.12
    0.6%
    51
    +0.10
    0.5%
    416
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.12
    0.05
    686
    +0.10
    0.04
    132
    +0.10
    0.04
    Negative Logits
     comrades
    -0.68
     Honour
    -0.65
    odox
    -0.65
    hod
    -0.64
     srfAttach
    -0.63
    ĪĴ
    -0.63
    hair
    -0.60
     dstg
    -0.60
     Eternity
    -0.60
    qus
    -0.60
    POSITIVE LOGITS
     worldwide
    1.19
     annually
    1.16
     yearly
    0.98
     globally
    0.93
     annual
    0.83
     nowadays
    0.80
     Worldwide
    0.75
    culosis
    0.73
     OECD
    0.72
    according
    0.71
    Activations Density 0.444%

    No Known Activations