© 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. 17183
    Prev
    Next
    INDEX
    Explanations

    words related to crime and legal issues

    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
    744
    +0.14
    0.7%
    167
    +0.10
    0.4%
    195
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.14
    0.01
    628
    +0.10
    0.01
    232
    +0.09
    0.01
    Negative Logits
    è¦ļéĨĴ
    -1.00
    akings
    -0.73
     overhead
    -0.68
     stakes
    -0.66
    ingo
    -0.66
     Kinnikuman
    -0.65
     sorting
    -0.65
     Doomsday
    -0.65
    redit
    -0.65
     separating
    -0.65
    POSITIVE LOGITS
    pected
    1.36
    pect
    1.35
    pecting
    1.24
    pects
    1.23
    pic
    1.23
    annah
    1.19
    pir
    1.12
    cept
    0.98
    sex
    0.95
    ethe
    0.93
    Activations Density 0.012%

    No Known Activations