© 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. 4442
    Prev
    Next
    INDEX
    Explanations

    sentences related to opinions or personal experiences

    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
    689
    +0.11
    0.5%
    617
    +0.10
    0.5%
    598
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.11
    0.05
    45
    +0.10
    0.04
    393
    +0.10
    0.07
    Negative Logits
    Optional
    -0.60
    tnc
    -0.58
    Alternatively
    -0.58
    ery
    -0.57
    ity
    -0.57
    iste
    -0.56
    upper
    -0.54
    natureconservancy
    -0.54
     substitutes
    -0.53
    akia
    -0.53
    POSITIVE LOGITS
     lately
    1.00
    recent
    0.93
    since
    0.90
    successfully
    0.86
     anecd
    0.84
     culminating
    0.82
     hasn
    0.82
     since
    0.81
    htaking
    0.81
     countless
    0.78
    Activations Density 0.595%

    No Known Activations