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

    Neuronpedia

    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. 18396
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or intensifiers such as "fucking," "freaking," and "literal."

    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
    48
    +0.10
    0.5%
    137
    +0.10
    0.4%
    192
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.10
    0.01
    306
    +0.10
    0.02
    331
    +0.09
    0.02
    Negative Logits
    Edit
    -0.84
    inel
    -0.84
    BIL
    -0.81
    knit
    -0.81
    ãĤ¢ãĥ«
    -0.77
    Folder
    -0.76
    Msg
    -0.76
    Mesh
    -0.75
     behavi
    -0.72
    Trust
    -0.70
    POSITIVE LOGITS
     kidding
    1.00
     hell
    0.84
     idiot
    0.81
     stink
    0.80
     thing
    0.79
     shit
    0.79
     bastard
    0.79
     asshole
    0.79
     retard
    0.79
     christ
    0.77
    Activations Density 0.031%

    No Known Activations