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. 23621
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used for comparisons or similes

    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
    322
    +0.10
    0.5%
    511
    +0.10
    0.4%
    632
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.10
    0.04
    172
    +0.10
    0.04
    647
    +0.08
    0.03
    Negative Logits
    çīĪ
    -0.65
    oller
    -0.65
    OSE
    -0.54
     Mandatory
    -0.54
    acent
    -0.54
     Mellon
    -0.53
     lockdown
    -0.51
    lish
    -0.50
    CCC
    -0.49
     Noble
    -0.49
    POSITIVE LOGITS
     regards
    0.95
    phy
    0.94
    pects
    0.91
     evidenced
    0.90
    par
    0.87
     opposed
    0.85
    bestos
    0.83
    well
    0.82
     fuck
    0.81
    phalt
    0.81
    Activations Density 0.101%

    No Known Activations