© 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. 22476
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rand."

    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
    288
    +0.13
    0.6%
    574
    +0.11
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    574
    +0.13
    0.01
    376
    +0.11
    0.01
    357
    +0.11
    0.01
    Negative Logits
     dism
    -0.78
    ysis
    -0.70
     towed
    -0.66
     depos
    -0.63
     sight
    -0.61
     marrow
    -0.60
     circadian
    -0.59
     clay
    -0.59
     encour
    -0.59
     accumulating
    -0.58
    POSITIVE LOGITS
    olph
    1.26
    olf
    0.97
    wick
    0.97
    stad
    0.96
    igan
    0.94
    uin
    0.93
    emonium
    0.83
    lich
    0.80
    alf
    0.79
    ian
    0.78
    Activations Density 0.013%

    No Known Activations