© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'being'

    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
    102
    +0.12
    0.6%
    566
    +0.11
    0.5%
    297
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.04
    297
    +0.11
    0.04
    55
    +0.11
    0.04
    Negative Logits
    PsyNetMessage
    -0.76
     Dag
    -0.69
    inav
    -0.65
    robat
    -0.65
     Beginning
    -0.61
    ère
    -0.59
    eva
    -0.59
     sovere
    -0.59
     Surv
    -0.59
     Lag
    -0.58
    POSITIVE LOGITS
     able
    1.15
     eaten
    0.92
     discussed
    0.91
     replaced
    0.91
     consumed
    0.91
     phased
    0.88
     touted
    0.88
     chased
    0.87
     hailed
    0.87
     considered
    0.87
    Activations Density 0.066%

    No Known Activations