© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23987
    Prev
    Next
    INDEX
    Explanations

    phrases related to fighting for social and political change

    oai_token-act-pair · gpt-4o-miniTriggered 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
    650
    +0.13
    0.6%
    272
    +0.10
    0.5%
    287
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.06
    650
    +0.10
    0.05
    642
    +0.09
    0.03
    Negative Logits
    nikov
    -0.83
    DragonMagazine
    -0.81
    ustomed
    -0.79
    pmwiki
    -0.76
     puzz
    -0.75
    etheless
    -0.74
     Zup
    -0.72
     nervously
    -0.69
     guiActiveUn
    -0.68
    Obs
    -0.67
    POSITIVE LOGITS
     mankind
    1.05
     humankind
    1.01
     humanity
    0.96
     injust
    0.93
     prosperity
    0.91
     revolution
    0.89
     oppressed
    0.87
     democrat
    0.86
     injustice
    0.86
     Socialism
    0.85
    Activations Density 0.376%

    No Known Activations