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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8206
    Prev
    Next
    INDEX
    Explanations

    phrases related to fairness and equity

    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
    362
    +0.17
    0.8%
    660
    +0.10
    0.5%
    387
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    387
    +0.17
    0.05
    362
    +0.10
    0.06
    159
    +0.10
    0.05
    Negative Logits
    hops
    -0.96
    aunts
    -0.96
    steps
    -0.85
    lees
    -0.82
    events
    -0.81
    notes
    -0.80
    planes
    -0.80
    stones
    -0.79
    Experts
    -0.79
    laws
    -0.79
    POSITIVE LOGITS
     outcome
    1.12
     environment
    1.11
     relationship
    1.11
     solution
    1.10
     atmosphere
    1.03
     complexion
    0.98
     outlook
    0.98
     response
    0.98
     disposition
    0.97
     version
    0.96
    Activations Density 0.230%

    No Known Activations