© 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. 20137
    Prev
    Next
    INDEX
    Explanations

    phrases related to feedback processes

    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
    191
    +0.11
    0.5%
    126
    +0.09
    0.4%
    420
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.11
    0.01
    26
    +0.09
    0.01
    191
    +0.09
    0.01
    Negative Logits
    isms
    -0.67
    ident
    -0.60
    isman
    -0.60
    ijn
    -0.59
     Scotia
    -0.58
    ities
    -0.57
     compr
    -0.57
     solved
    -0.56
    pp
    -0.56
    ESS
    -0.55
    POSITIVE LOGITS
    oras
    0.99
    stocks
    0.96
    fed
    0.94
    ora
    0.93
    parser
    0.92
    elsen
    0.88
    entary
    0.87
     fed
    0.83
    forward
    0.80
     hungry
    0.79
    Activations Density 0.030%

    No Known Activations