© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and bureaucratic language

    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
    393
    +0.16
    0.7%
    362
    +0.13
    0.6%
    608
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.08
    608
    +0.13
    0.06
    393
    +0.10
    0.05
    Negative Logits
    cil
    -0.86
    SPONSORED
    -0.81
    âĿ
    -0.75
    wart
    -0.72
    Chart
    -0.70
    nb
    -0.68
    hover
    -0.68
    aves
    -0.68
    ranged
    -0.67
    tackle
    -0.67
    POSITIVE LOGITS
     feasibility
    1.42
     possibility
    1.31
     legality
    1.19
     situation
    1.19
     merits
    1.19
     adequ
    1.13
     implications
    1.11
     contents
    1.11
     totality
    1.10
     ramifications
    1.09
    Activations Density 0.252%

    No Known Activations