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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 34
    Prev
    Next
    INDEX
    Explanations

    financial and technological terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    447
    +0.19
    0.9%
    481
    +0.16
    0.8%
    495
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.23
    575
    +0.16
    0.20
    225
    +0.10
    0.17
    Negative Logits
    stood
    -0.78
     pestic
    -0.73
    SPONSORED
    -0.67
     GN
    -0.60
     therap
    -0.52
    ãĤ«
    -0.52
     Sark
    -0.51
    audi
    -0.51
     Hobby
    -0.51
     Aerial
    -0.50
    POSITIVE LOGITS
     onto
    1.12
     anonymously
    1.11
     cheaply
    1.09
     WITHOUT
    1.07
     manually
    1.06
     accordingly
    1.06
     wherever
    1.05
     aloud
    1.04
     without
    1.03
     peacefully
    1.02
    Activations Density 4.661%

    No Known Activations