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

    Neuronpedia

    Jacobian LensNEW
    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. 1296
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and criminal activities

    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
    440
    +0.11
    0.5%
    28
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.10
    440
    +0.11
    0.08
    679
    +0.11
    0.09
    Negative Logits
     regener
    -0.87
     regenerate
    -0.85
     shedding
    -0.72
    ãĥķãĤ¡
    -0.72
     microbiome
    -0.70
     contempl
    -0.70
     sag
    -0.68
     thinner
    -0.68
    juries
    -0.67
     darker
    -0.67
    POSITIVE LOGITS
     Unfortunately
    1.32
     Then
    1.11
     Instead
    1.05
     Sadly
    1.01
     Luckily
    1.00
     However
    1.00
     Later
    0.99
     Eventually
    0.99
    Unfortunately
    0.97
     Afterwards
    0.96
    Activations Density 0.496%

    No Known Activations