© 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 EvalsExportsinterp-engineNEWAPI 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. 22963
    Prev
    Next
    INDEX
    Explanations

    references to "camp" and related terms

    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
    459
    +0.13
    0.6%
    314
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.13
    0.02
    126
    +0.11
    0.02
    288
    +0.11
    0.02
    Negative Logits
    lihood
    -0.77
     antioxid
    -0.69
    ctive
    -0.68
     nutrit
    -0.67
     magnification
    -0.65
     streng
    -0.62
     regress
    -0.61
    ulously
    -0.60
     sympt
    -0.58
     microscopic
    -0.58
    POSITIVE LOGITS
    fires
    1.34
    ground
    1.30
    grounds
    1.27
    fire
    1.23
    agna
    1.08
    camp
    1.07
    agne
    0.97
    anas
    0.93
    erness
    0.89
    bell
    0.88
    Activations Density 0.019%

    No Known Activations