© 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. 766
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural works

    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
    232
    +0.12
    0.5%
    314
    +0.10
    0.5%
    412
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.12
    145
    +0.10
    0.08
    314
    +0.10
    -0.01
    Negative Logits
     podium
    -0.80
     lect
    -0.78
     taxp
    -0.77
     porous
    -0.76
     sponsoring
    -0.74
     endors
    -0.74
     manufacturer
    -0.73
     regist
    -0.73
     sponsor
    -0.72
     statistic
    -0.72
    POSITIVE LOGITS
     Dreams
    1.23
     Days
    1.16
     Goodbye
    1.14
     Skies
    1.14
     Ruin
    1.11
     Dirty
    1.10
     Girl
    1.08
     Eyes
    1.08
     Tomorrow
    1.08
     Memories
    1.06
    Activations Density 1.409%

    No Known Activations