© 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 24576
    9. 8-RES_FS24576-JB
    11. 20077
    Prev
    Next
    INDEX
    Explanations

    sentences discussing political conflicts and human rights issues

    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
    640
    +0.31
    1.5%
    480
    +0.21
    1.1%
    160
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.31
    0.15
    160
    +0.21
    0.14
    442
    +0.17
    0.13
    Negative Logits
    xual
    -0.83
     casc
    -0.75
     commissions
    -0.71
     transitions
    -0.70
     circuits
    -0.68
     purs
    -0.68
     altern
    -0.67
     weekends
    -0.66
     regener
    -0.66
     incent
    -0.66
    POSITIVE LOGITS
    WASHINGTON
    1.38
    Published
    1.29
    SHARE
    1.29
    LOS
    1.24
    According
    1.21
    Sources
    1.21
    Posted
    1.21
    SAN
    1.20
    Advertisement
    1.20
    Article
    1.19
    Activations Density 0.425%

    No Known Activations