© 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. 19568
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and political activism

    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
    572
    +0.12
    0.5%
    418
    +0.10
    0.4%
    728
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.12
    0.03
    748
    +0.10
    0.02
    728
    +0.08
    0.02
    Negative Logits
    geoning
    -0.71
    DragonMagazine
    -0.64
     Investig
    -0.63
    etting
    -0.62
    UCT
    -0.60
    usterity
    -0.60
    士
    -0.59
     executions
    -0.59
    Thumbnail
    -0.57
    lopp
    -0.57
    POSITIVE LOGITS
     others
    1.10
     whoever
    0.85
     yours
    0.83
     coworkers
    0.80
     theirs
    0.77
     anyone
    0.73
     mates
    0.73
     anybody
    0.72
     strangers
    0.71
    everyone
    0.71
    Activations Density 0.127%

    No Known Activations