© 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. 18525
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or controversial statements

    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
    99
    +0.15
    0.7%
    326
    +0.13
    0.6%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.01
    99
    +0.13
    0.01
    13
    +0.10
    0.01
    Negative Logits
     Rite
    -0.82
    urgy
    -0.78
    effic
    -0.68
    VERTISEMENT
    -0.67
    ulatory
    -0.67
    ulators
    -0.67
    ulator
    -0.65
    usterity
    -0.65
    sav
    -0.65
    OTOS
    -0.64
    POSITIVE LOGITS
     defy
    1.01
     dare
    0.99
    evil
    0.92
     daring
    0.86
     boldly
    0.86
     Dare
    0.84
    ously
    0.83
     provoke
    0.81
     dared
    0.81
     presume
    0.81
    Activations Density 0.023%

    No Known Activations