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 24576
    5. 8-RES_FS24576-JB
    6. 7485
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to law enforcement

    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
    481
    +0.16
    0.7%
    756
    +0.12
    0.6%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.16
    -0.01
    300
    +0.12
    0.05
    718
    +0.10
    0.05
    Negative Logits
    natureconservancy
    -0.88
     Tycoon
    -0.76
     inhab
    -0.71
     demos
    -0.71
    Images
    -0.71
    izen
    -0.70
     orbits
    -0.70
     inhabit
    -0.69
     fertile
    -0.69
     prototype
    -0.69
    POSITIVE LOGITS
     levied
    1.38
     imposed
    1.38
     enforced
    1.15
     waived
    1.10
     issued
    1.09
     punitive
    1.09
     awarded
    1.07
     payable
    1.07
     deterrent
    1.01
     expire
    1.01
    Activations Density 0.438%

    No Known Activations