© 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. 7781
    Prev
    Next
    INDEX
    Explanations

    phrases related to land development and ownership

    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
    481
    +0.14
    0.6%
    586
    +0.12
    0.5%
    711
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.14
    0.04
    139
    +0.12
    0.05
    83
    +0.11
    0.04
    Negative Logits
    rossover
    -0.82
    aber
    -0.74
    psych
    -0.71
     matchup
    -0.70
    notations
    -0.70
    Coming
    -0.69
    ghazi
    -0.69
    reality
    -0.69
    20439
    -0.68
    violence
    -0.68
    POSITIVE LOGITS
     owns
    0.99
     oversaw
    0.93
     personally
    0.92
     himself
    0.91
     leased
    0.89
     patented
    0.89
     hired
    0.84
     instructed
    0.83
     donated
    0.82
     succeeded
    0.81
    Activations Density 0.636%

    No Known Activations