Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 840
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of inheritance

    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
    343
    +0.14
    0.6%
    335
    +0.12
    0.6%
    409
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.01
    343
    +0.12
    0.01
    91
    +0.09
    0.01
    Negative Logits
    trak
    -0.77
    mpeg
    -0.73
    youtu
    -0.69
    apa
    -0.69
    aeper
    -0.69
    eller
    -0.68
    aredevil
    -0.67
    ournal
    -0.67
    Hour
    -0.67
    ulhu
    -0.66
    POSITIVE LOGITS
     inherited
    1.02
     inheritance
    1.01
     inherit
    0.95
     wealth
    0.94
     inher
    0.92
     responsibility
    0.83
     lineage
    0.81
     riches
    0.80
     heritage
    0.75
     ownership
    0.73
    Activations Density 0.026%

    No Known Activations