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. 666
    Prev
    Next
    INDEX
    Explanations

    keywords related to blockchain technology

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    288
    +0.17
    0.8%
    481
    +0.14
    0.6%
    447
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.17
    0.02
    578
    +0.14
    0.01
    288
    +0.14
    0.02
    Negative Logits
     Eisenhower
    -0.84
     Phelps
    -0.82
     Simpson
    -0.82
     Hodg
    -0.78
    hiro
    -0.76
    baugh
    -0.76
    lee
    -0.76
    swick
    -0.75
     Upton
    -0.73
     Sop
    -0.70
    POSITIVE LOGITS
     technology
    1.05
     technologies
    0.97
    technology
    0.96
     ledger
    0.91
     blockchain
    0.88
     ecosystem
    0.83
    assets
    0.83
     Blockchain
    0.82
     architectures
    0.81
     systems
    0.79
    Activations Density 0.025%

    No Known Activations