© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    mentions of police brutality

    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
    87
    +0.22
    1.1%
    756
    +0.20
    1.0%
    2
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.22
    -0.01
    87
    +0.20
    -0.04
    86
    +0.09
    0.05
    Negative Logits
     âĢº
    -0.66
    earable
    -0.65
     Finder
    -0.63
    ocular
    -0.61
    igraph
    -0.59
    rawler
    -0.59
    ubuntu
    -0.59
     pupil
    -0.57
    \)
    -0.57
    ellery
    -0.57
    POSITIVE LOGITS
     trillions
    0.96
     patri
    0.88
     MSM
    0.87
     complicit
    0.85
     pathetic
    0.84
     fucking
    0.83
    erity
    0.81
     neocons
    0.81
     hypocrisy
    0.81
     goddamn
    0.80
    Activations Density 1.543%

    No Known Activations