© 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 EvalsExportsinterp-engineNEWAPI 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. 13253
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions, physical placements, and individuals being told what to do

    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
    447
    +0.18
    0.8%
    454
    +0.11
    0.5%
    584
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.18
    0.05
    469
    +0.11
    0.03
    665
    +0.10
    0.04
    Negative Logits
     predictions
    -0.66
     inspires
    -0.66
     VIDEOS
    -0.66
     nails
    -0.65
     inspiring
    -0.65
    aclysm
    -0.65
     nostalg
    -0.64
    akes
    -0.64
     inspire
    -0.63
    bows
    -0.63
    POSITIVE LOGITS
     Detention
    1.00
     Psychiatric
    0.97
     quarantine
    0.95
     psychiatric
    0.94
     probation
    0.92
     detention
    0.87
     Correctional
    0.86
    ospital
    0.85
     boarding
    0.84
     custody
    0.84
    Activations Density 0.233%

    No Known Activations