© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    words related to controversial or inappropriate topics, often related to social or political 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
    251
    +0.13
    0.6%
    123
    +0.10
    0.5%
    331
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.09
    251
    +0.10
    0.06
    326
    +0.10
    0.06
    Negative Logits
    Ability
    -0.77
    lihood
    -0.73
    Solution
    -0.72
    DIV
    -0.71
    ODUCT
    -0.71
    Information
    -0.69
    RESULTS
    -0.69
    Internal
    -0.69
     Development
    -0.69
    EGIN
    -0.68
    POSITIVE LOGITS
     bikini
    0.88
    punk
    0.85
     blaster
    0.81
     boobs
    0.81
     kisses
    0.80
     disco
    0.79
     tits
    0.79
     themed
    0.79
    ovies
    0.78
     fries
    0.77
    Activations Density 0.504%

    No Known Activations