© 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. 24356
    Prev
    Next
    INDEX
    Explanations

    terms related to social connection and community engagement

    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
    87
    +0.26
    1.4%
    459
    +0.13
    0.6%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.26
    0.06
    756
    +0.13
    -0.02
    641
    +0.10
    0.07
    Negative Logits
     Clapper
    -0.72
     Manafort
    -0.66
     Corker
    -0.65
    )?
    -0.64
     anyway
    -0.59
    assium
    -0.58
     pse
    -0.58
     Bearing
    -0.58
     Comey
    -0.58
     bail
    -0.58
    POSITIVE LOGITS
     creativity
    0.89
     innovative
    0.88
     passionate
    0.82
     immersive
    0.80
     innov
    0.79
     innovate
    0.77
     creative
    0.76
     inspirational
    0.74
    iscovery
    0.74
     inspiring
    0.73
    Activations Density 0.881%

    No Known Activations