© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6923
    Prev
    Next
    INDEX
    Explanations

    percentage values or fractions

    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
    339
    +0.11
    0.5%
    166
    +0.10
    0.4%
    608
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.11
    0.03
    409
    +0.10
    0.03
    597
    +0.09
    0.03
    Negative Logits
    CLA
    -0.64
     grouping
    -0.64
    ãĤ¡
    -0.60
    dump
    -0.59
    ide
    -0.58
    etic
    -0.58
    uality
    -0.57
    AMI
    -0.57
    ibe
    -0.56
    no
    -0.56
    POSITIVE LOGITS
     Sevent
    0.70
     Mississ
    0.70
    ousand
    0.68
    çĶ°
    0.67
     earners
    0.64
     GDP
    0.64
     Britons
    0.63
     dozen
    0.61
     Americans
    0.61
     Aberdeen
    0.59
    Activations Density 0.052%

    No Known Activations