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

    Neuronpedia

    Jacobian LensNEW
    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. 19750
    Prev
    Next
    INDEX
    Explanations

    information about media and entertainment news

    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
    314
    +0.12
    0.5%
    122
    +0.10
    0.5%
    48
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.09
    48
    +0.10
    0.07
    37
    +0.10
    0.06
    Negative Logits
     seiz
    -0.85
     answ
    -0.72
     behav
    -0.69
     habits
    -0.69
    rogens
    -0.67
     incent
    -0.67
     lawy
    -0.66
     obser
    -0.66
     bluff
    -0.65
     myster
    -0.65
    POSITIVE LOGITS
    ï¸ı
    0.88
    stellar
    0.81
    é¾į
    0.79
     Founder
    0.79
    audi
    0.76
     Originally
    0.75
    MpServer
    0.74
    姫
    0.73
    series
    0.71
    ï¸
    0.70
    Activations Density 0.251%

    No Known Activations