© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12016
    Prev
    Next
    INDEX
    Explanations

    personal details such as ages, job titles, and locations

    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
    420
    +0.13
    0.6%
    545
    +0.10
    0.5%
    752
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.13
    0.06
    152
    +0.10
    0.05
    711
    +0.10
    0.03
    Negative Logits
     iPads
    -0.84
    zees
    -0.78
    ravings
    -0.75
     VIDEOS
    -0.73
     Committees
    -0.72
     Puzzles
    -0.71
    bugs
    -0.71
    ombies
    -0.70
     idiots
    -0.70
     Parties
    -0.70
    POSITIVE LOGITS
     member
    0.95
     descendant
    0.94
     accountant
    0.94
     lawyer
    0.93
     graduate
    0.92
     veteran
    0.90
     attorney
    0.89
     consultant
    0.88
     supporter
    0.87
     entrepreneur
    0.87
    Activations Density 0.204%

    No Known Activations