© 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. 5928
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by proper nouns or key terms in legal settings

    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
    726
    +0.12
    0.5%
    514
    +0.11
    0.5%
    541
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    284
    +0.11
    0.02
    701
    +0.10
    0.02
    Negative Logits
     outl
    -0.71
     multim
    -0.69
     pige
    -0.64
     pim
    -0.63
     reconnect
    -0.62
    emetery
    -0.62
     redundancy
    -0.61
     steep
    -0.59
     fictitious
    -0.58
     borderline
    -0.58
    POSITIVE LOGITS
    ield
    0.83
    emon
    0.82
    neau
    0.81
    ð
    0.80
    ption
    0.80
    orie
    0.80
    neum
    0.79
    hyde
    0.79
    isans
    0.77
    aki
    0.73
    Activations Density 0.068%

    No Known Activations