© 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. 12418
    Prev
    Next
    INDEX
    Explanations

    phrases that involve futuristic or speculative elements

    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
    480
    +0.16
    0.7%
    314
    +0.12
    0.5%
    23
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.12
    352
    +0.12
    0.12
    426
    +0.09
    0.10
    Negative Logits
     guiActiveUnfocused
    -0.75
     scattering
    -0.72
     lodging
    -0.68
     Kirin
    -0.67
     Palest
    -0.67
     Droid
    -0.67
     Libyan
    -0.66
     Moroccan
    -0.63
     scatter
    -0.62
     Izan
    -0.61
    POSITIVE LOGITS
    ¹
    1.08
    º
    1.01
    £
    0.99
    Pg
    0.95
    agree
    0.95
    Į
    0.94
    ¢
    0.93
    Ĵ
    0.92
    ı
    0.90
    Ĭ
    0.90
    Activations Density 0.259%

    No Known Activations