© 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. 14361
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental interventions and programs

    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
    480
    +0.13
    0.6%
    575
    +0.11
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.08
    575
    +0.11
    0.08
    225
    +0.11
    0.07
    Negative Logits
    ãĥĥãĥī
    -0.70
    ãĥį
    -0.64
    noon
    -0.64
     VID
    -0.62
    ãĤ¨ãĥ«
    -0.60
     IMAGES
    -0.59
    STON
    -0.58
     predicament
    -0.57
     Borough
    -0.57
     unbeliev
    -0.57
    POSITIVE LOGITS
    hips
    1.33
     thereof
    1.23
     etc
    1.19
    mith
    1.11
    uggest
    0.98
    paces
    0.98
     thereto
    0.96
    poons
    0.95
    cript
    0.92
    hip
    0.92
    Activations Density 0.374%

    No Known Activations