© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws 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
    217
    +0.10
    0.5%
    454
    +0.10
    0.5%
    439
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.10
    0.05
    439
    +0.10
    0.05
    310
    +0.10
    0.05
    Negative Logits
    trak
    -0.78
    assing
    -0.78
    ierre
    -0.78
    razil
    -0.63
    urrection
    -0.62
    ynski
    -0.62
    prints
    -0.61
    involved
    -0.59
    rap
    -0.58
    tra
    -0.58
    POSITIVE LOGITS
     by
    1.05
     unto
    0.85
     via
    0.83
    ãĥ¼ãĥĨ
    0.80
     herein
    0.75
     BY
    0.73
     orally
    0.72
     courtesy
    0.72
     aback
    0.72
     to
    0.71
    Activations Density 0.242%

    No Known Activations