© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12198
    Prev
    Next
    INDEX
    Explanations

    phrases related to announcements, promotions, and user engagement in contexts such as media partnerships, global game releases, and crowdfunding campaigns

    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
    373
    +0.12
    0.6%
    343
    +0.10
    0.5%
    483
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.03
    348
    +0.10
    0.06
    671
    +0.10
    0.04
    Negative Logits
    DNA
    -0.64
    erness
    -0.57
    dinand
    -0.57
    cientious
    -0.56
    SHIP
    -0.56
    ervatives
    -0.56
    istor
    -0.56
    DEM
    -0.54
    eln
    -0.54
    acement
    -0.54
    POSITIVE LOGITS
     importantly
    0.95
     furthermore
    0.81
     interestingly
    0.78
     aside
    0.74
     moreover
    0.73
     incidentally
    0.71
     nutshell
    0.71
     proble
    0.69
     notwithstanding
    0.68
     suspic
    0.67
    Activations Density 0.536%

    No Known Activations