© 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 3072
    9. 8-RES_FS3072-JB
    11. 258
    Prev
    Next
    INDEX
    Explanations

    references to political events or actions

    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
    694
    +0.09
    0.4%
    464
    +0.09
    0.4%
    308
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.13
    232
    +0.09
    0.07
    316
    +0.09
    0.07
    Negative Logits
    ŃĶ
    -0.69
    ccording
    -0.65
     tremend
    -0.63
    Ô
    -0.60
     nonviolent
    -0.58
     entreprene
    -0.58
     subter
    -0.57
    senal
    -0.56
    ãĤ¼ãĤ¦ãĤ¹
    -0.54
    ij士
    -0.54
    POSITIVE LOGITS
    ↵
    1.68
    <|endoftext|>
    1.26
    ↵↵
    1.08
    SPONSORED
    0.93
     Again
    0.66
     Alternatively
    0.62
     Includes
    0.61
    ;}
    0.61
     Also
    0.60
     Unsure
    0.60
    Activations Density 1.121%

    No Known Activations