© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, publications, and opinions, particularly on hot topics

    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
    +0.46
    2.3%
    7
    +0.14
    0.7%
    625
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.46
    0.01
    351
    +0.14
    0.05
    266
    +0.10
    0.09
    Negative Logits
    ullivan
    -0.55
    edia
    -0.54
    ß
    -0.53
    auri
    -0.52
     Skydragon
    -0.52
     Starr
    -0.51
    cohol
    -0.51
    atown
    -0.51
     Qiao
    -0.51
    hoe
    -0.50
    POSITIVE LOGITS
     thereof
    1.18
     accordingly
    1.09
     them
    1.08
     theirs
    1.06
     thereto
    1.04
     therein
    0.98
     THEM
    0.85
     it
    0.81
    them
    0.80
     yours
    0.77
    Activations Density 1.295%

    No Known Activations