© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    details related to security and law enforcement operations

    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
    601
    +0.12
    0.5%
    665
    +0.11
    0.5%
    265
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.12
    0.05
    651
    +0.11
    0.06
    530
    +0.10
    0.04
    Negative Logits
     crou
    -0.69
     mistaken
    -0.68
     pseudonym
    -0.65
     Originally
    -0.64
     tolerated
    -0.63
     reproduced
    -0.63
     volunteered
    -0.61
     ingenious
    -0.61
     vou
    -0.61
    ocal
    -0.60
    POSITIVE LOGITS
     2019
    1.10
     tomorrow
    1.09
     deadline
    1.03
     next
    1.00
     anniversary
    0.99
     showdown
    0.96
     recess
    0.95
     finals
    0.94
     2018
    0.92
     2021
    0.91
    Activations Density 0.442%

    No Known Activations