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. 795
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions and interpersonal relationships

    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
    506
    +0.10
    0.5%
    14
    +0.10
    0.5%
    153
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.10
    0.07
    528
    +0.10
    0.07
    304
    +0.09
    0.07
    Negative Logits
    ogle
    -0.69
    elight
    -0.68
    pletion
    -0.67
    duc
    -0.67
    kie
    -0.66
    bara
    -0.66
    Reader
    -0.65
    livion
    -0.65
    phies
    -0.64
    ruption
    -0.60
    POSITIVE LOGITS
     mutually
    1.46
     together
    1.16
     insepar
    1.16
     jointly
    1.10
     respectively
    1.04
    together
    1.01
     mutual
    1.00
     Together
    0.98
     respective
    0.97
     agree
    0.96
    Activations Density 2.987%

    No Known Activations