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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9962
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    756
    +0.11
    0.5%
    452
    +0.11
    0.5%
    564
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.11
    0.05
    690
    +0.11
    0.06
    452
    +0.10
    0.05
    Negative Logits
    yss
    -0.76
     RTX
    -0.74
    venture
    -0.73
     experien
    -0.68
     Trance
    -0.68
    Jet
    -0.67
     sensations
    -0.65
     Bucc
    -0.65
    naissance
    -0.65
    culus
    -0.65
    POSITIVE LOGITS
     enforced
    1.38
     repealed
    1.34
     enacted
    1.34
     enforce
    1.32
     prohibiting
    1.30
    enforcement
    1.27
     ratified
    1.25
     promulg
    1.18
     governing
    1.17
     regulating
    1.17
    Activations Density 0.894%

    No Known Activations