© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    personal reflections and religious expressions

    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
    +0.13
    0.6%
    650
    +0.10
    0.4%
    430
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.13
    0.06
    665
    +0.10
    0.06
    764
    +0.10
    0.04
    Negative Logits
     Marino
    -0.82
    anyahu
    -0.65
     loophole
    -0.63
     caveat
    -0.63
     typo
    -0.62
     Didn
    -0.62
     Moreno
    -0.61
     Siren
    -0.58
     Shark
    -0.57
    herry
    -0.57
    POSITIVE LOGITS
     interact
    1.04
     perce
    0.89
     interacts
    0.88
     perceive
    0.87
     interacting
    0.86
     communicate
    0.85
     environments
    0.74
     interactions
    0.74
     interpersonal
    0.72
     interacted
    0.72
    Activations Density 0.620%

    No Known Activations