© 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. 14634
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instant" followed by a numbered sequence

    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
    288
    +0.12
    0.5%
    728
    +0.10
    0.5%
    394
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.12
    0.01
    728
    +0.10
    0.01
    162
    +0.10
    0.01
    Negative Logits
    ALD
    -0.83
    xual
    -0.80
    pherd
    -0.77
    llah
    -0.72
    umbing
    -0.71
    ^^^^
    -0.71
    ETS
    -0.70
    ramids
    -0.70
    bard
    -0.69
    anners
    -0.69
    POSITIVE LOGITS
    aneously
    2.01
     gratification
    1.51
    aneous
    1.49
    iation
    1.26
    iated
    1.21
    iations
    1.19
     replay
    1.13
    iating
    1.12
    iate
    1.03
     messenger
    0.97
    Activations Density 0.016%

    No Known Activations