© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 73
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    70
    +0.13
    0.6%
    75
    +0.09
    0.4%
    83
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.13
    0.07
    164
    +0.09
    0.06
    647
    +0.08
    0.04
    Negative Logits
    othal
    -0.77
    udic
    -0.74
    zanne
    -0.74
    emort
    -0.74
    undy
    -0.73
    vable
    -0.72
    vid
    -0.72
    aretz
    -0.72
    edin
    -0.71
    asions
    -0.70
    POSITIVE LOGITS
    meaning
    0.95
     abbre
    0.91
    literally
    0.87
     Meaning
    0.81
    ãĤ´
    0.80
     shorthand
    0.78
     Literally
    0.78
     Beautiful
    0.78
     Dwell
    0.77
     acronym
    0.75
    Activations Density 1.186%

    No Known Activations