© 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. 18723
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing assistance and support for group activities

    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
    745
    +0.12
    0.6%
    388
    +0.12
    0.6%
    735
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.07
    566
    +0.12
    0.05
    354
    +0.12
    0.05
    Negative Logits
    Bey
    -0.71
     defiance
    -0.68
     rebellion
    -0.66
     Bundy
    -0.65
    ierre
    -0.64
    olph
    -0.63
    NAS
    -0.63
    assault
    -0.63
     Amid
    -0.62
     daring
    -0.61
    POSITIVE LOGITS
     notify
    1.10
     automatically
    0.90
     reimburse
    0.88
     advise
    0.88
     refund
    0.88
     evict
    0.87
     reimb
    0.85
     enforce
    0.85
     recommend
    0.84
     arrange
    0.83
    Activations Density 0.440%

    No Known Activations