© 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. 17388
    Prev
    Next
    INDEX
    Explanations

    references to opposition or dissent

    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
    679
    +0.13
    0.6%
    276
    +0.12
    0.6%
    228
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.13
    0.02
    228
    +0.12
    0.01
    214
    +0.10
    0.01
    Negative Logits
    Interstitial
    -0.70
    enegger
    -0.68
    negie
    -0.63
    brate
    -0.62
     Fork
    -0.61
    çīĪ
    -0.61
     Learns
    -0.61
     Migration
    -0.60
     emanc
    -0.60
    è¯
    -0.60
    POSITIVE LOGITS
    onent
    1.74
    onents
    1.59
    osition
    1.57
    osite
    1.56
    ortun
    1.56
    osing
    1.34
    ression
    1.31
    ressive
    1.31
    ressor
    1.26
    osed
    1.24
    Activations Density 0.017%

    No Known Activations