© 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. 11103
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and learning, specifically focused on culinary arts and climbing routes

    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
    559
    +0.12
    0.5%
    580
    +0.09
    0.4%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.12
    0.02
    537
    +0.09
    0.02
    261
    +0.09
    0.02
    Negative Logits
    amental
    -0.65
    winter
    -0.65
     Judgment
    -0.60
     msec
    -0.60
    é¾į
    -0.59
     repr
    -0.59
    PDATE
    -0.59
     judgment
    -0.58
     happiest
    -0.57
     Amnesty
    -0.57
    POSITIVE LOGITS
     dots
    1.26
     knot
    0.87
    links
    0.87
     knots
    0.85
     seamlessly
    0.83
    chain
    0.83
     cables
    0.83
     wires
    0.82
     linking
    0.82
     Ethernet
    0.81
    Activations Density 0.205%

    No Known Activations