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 3072
    5. 8-RES_FS3072-JB
    6. 2883
    Prev
    Next
    INDEX
    Explanations

    verbs related to handling and storing data, especially in a technological context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    91
    +0.12
    0.5%
    507
    +0.09
    0.4%
    664
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.14
    70
    +0.09
    0.12
    507
    +0.09
    0.10
    Negative Logits
    arij
    -0.76
    soType
    -0.73
     Cruiser
    -0.68
    obia
    -0.67
     condem
    -0.65
    ansion
    -0.61
    zai
    -0.61
    alian
    -0.61
    ismo
    -0.61
    ĸļ
    -0.60
    POSITIVE LOGITS
     incoming
    0.95
     certain
    0.92
     various
    0.88
     inputs
    0.88
     goods
    0.87
     messages
    0.85
     efficiently
    0.82
     tasks
    0.82
     information
    0.81
     objects
    0.80
    Activations Density 1.981%

    No Known Activations