© 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. 5440
    Prev
    Next
    INDEX
    Explanations

    political and news-related names and terms

    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
    145
    +0.11
    0.5%
    483
    +0.11
    0.5%
    324
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.06
    425
    +0.11
    0.05
    145
    +0.11
    0.05
    Negative Logits
    depending
    -0.69
    ONSORED
    -0.61
    ENCY
    -0.58
    Anyway
    -0.58
     Contrast
    -0.57
    "))
    -0.56
    ¬¼
    -0.56
     LET
    -0.56
    uries
    -0.55
    CONCLUS
    -0.55
    POSITIVE LOGITS
     and
    0.94
    ortium
    0.82
     Jr
    0.78
     AND
    0.75
     &
    0.72
    mith
    0.69
     nor
    0.69
    nir
    0.66
    and
    0.65
    bie
    0.64
    Activations Density 0.460%

    No Known Activations