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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18728
    Prev
    Next
    INDEX
    Explanations

    legal and judicial terms related to court cases and decisions

    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
    409
    +0.14
    0.6%
    329
    +0.11
    0.5%
    301
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.05
    636
    +0.11
    0.03
    409
    +0.11
    0.03
    Negative Logits
    »Ĵ
    -0.82
    7601
    -0.79
    beck
    -0.72
     Plenty
    -0.71
    ochond
    -0.69
    etting
    -0.68
    ettes
    -0.68
    erness
    -0.66
    Chat
    -0.66
    shaw
    -0.66
    POSITIVE LOGITS
     decree
    0.96
     injunction
    0.93
     presumption
    0.92
     longstanding
    0.92
     decision
    0.91
     prohibition
    0.89
     convictions
    0.87
     moratorium
    0.86
     judgment
    0.86
     directive
    0.85
    Activations Density 0.187%

    No Known Activations