© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    verbs in past tense indicating the beginning or initiation of an action or process

    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
    86
    +0.13
    0.6%
    566
    +0.11
    0.5%
    482
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.06
    545
    +0.11
    0.05
    62
    +0.09
    0.04
    Negative Logits
    obi
    -0.74
     entirety
    -0.71
    inals
    -0.67
    ighth
    -0.66
    omb
    -0.65
    warts
    -0.63
    aths
    -0.62
    icator
    -0.62
    rero
    -0.61
    âĨij
    -0.61
    POSITIVE LOGITS
     anew
    1.19
     behaving
    0.91
     noticing
    0.90
     experimenting
    0.84
     bothering
    0.83
     raining
    0.80
     fuss
    0.77
     dating
    0.77
     acting
    0.76
     banging
    0.76
    Activations Density 0.075%

    No Known Activations