© 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 EvalsExportsinterp-engineNEWAPI 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. 20932
    Prev
    Next
    INDEX
    Explanations

    questions or statements related to philosophical or ideological beliefs

    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
    608
    +0.12
    0.5%
    458
    +0.12
    0.5%
    167
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.12
    0.03
    588
    +0.12
    0.04
    284
    +0.10
    0.04
    Negative Logits
    aston
    -0.75
    Tips
    -0.72
    akening
    -0.71
    IDA
    -0.71
    ONSORED
    -0.69
    bryce
    -0.69
    irez
    -0.68
     Vaugh
    -0.68
    tips
    -0.67
     misunder
    -0.66
    POSITIVE LOGITS
     reality
    0.72
     UX
    0.70
     noun
    0.68
     democracy
    0.67
     nons
    0.65
     Magic
    0.65
     sorcery
    0.64
     capitalism
    0.64
     autos
    0.63
     automobiles
    0.63
    Activations Density 0.173%

    No Known Activations