© 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. 2345
    Prev
    Next
    INDEX
    Explanations

    phrases related to photography and artistic techniques

    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
    331
    +0.15
    0.7%
    329
    +0.11
    0.5%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.15
    0.05
    181
    +0.11
    0.04
    153
    +0.10
    0.03
    Negative Logits
    ida
    -0.78
    eks
    -0.78
    atti
    -0.76
    iden
    -0.75
     Kaplan
    -0.72
    ati
    -0.72
     Vance
    -0.72
    Į
    -0.71
    idas
    -0.71
    idan
    -0.70
    POSITIVE LOGITS
     gas
    0.91
    roleum
    0.89
    hyde
    0.88
     water
    0.84
     plasma
    0.83
     Gas
    0.83
     nuclear
    0.83
     Milk
    0.82
     Hybrid
    0.81
     coal
    0.81
    Activations Density 0.287%

    No Known Activations