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. 23038
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or feelings of being fortunate

    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
    101
    +0.11
    0.5%
    139
    +0.11
    0.5%
    610
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.11
    0.02
    49
    +0.11
    0.02
    139
    +0.10
    0.02
    Negative Logits
    amental
    -0.73
    terness
    -0.73
    leaf
    -0.73
    intensive
    -0.66
    spir
    -0.66
     tightening
    -0.65
    chlor
    -0.65
    grave
    -0.61
    ãĤ¦ãĤ¹
    -0.61
    ohm
    -0.61
    POSITIVE LOGITS
     fortunate
    1.03
     lucky
    0.99
     survived
    0.93
     privileged
    0.89
     befriend
    0.85
    ilege
    0.84
    pez
    0.84
     survive
    0.83
     sheltered
    0.80
     surviving
    0.80
    Activations Density 0.098%

    No Known Activations