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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 40122
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    679
    +0.14
    0.6%
    726
    +0.12
    0.6%
    540
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.14
    0.01
    726
    +0.12
    0.01
    216
    +0.10
    0.01
    Negative Logits
    ench
    -0.75
    artney
    -0.72
    Jet
    -0.69
    bill
    -0.69
    pac
    -0.68
    oning
    -0.67
    far
    -0.67
    gart
    -0.66
    leeve
    -0.66
    oil
    -0.66
    POSITIVE LOGITS
     decisions
    1.02
     processes
    0.99
     process
    0.95
     oversight
    0.88
     mechanisms
    0.87
     exerc
    0.86
     authority
    0.86
     committees
    0.86
    eering
    0.84
     sessions
    0.83
    Activations Density 0.015%

    No Known Activations