© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9611
    Prev
    Next
    INDEX
    Explanations

    single quotation marks used to convey direct speech or emphasize statements

    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
    314
    +0.15
    0.7%
    160
    +0.13
    0.6%
    205
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.15
    0.02
    102
    +0.13
    0.02
    205
    +0.09
    0.02
    Negative Logits
     dwell
    -0.73
     Janeiro
    -0.66
     turnover
    -0.64
     tabl
    -0.64
     Dani
    -0.64
     Mehran
    -0.63
     rental
    -0.63
     Nanto
    -0.63
     Syd
    -0.63
     dwelling
    -0.62
    POSITIVE LOGITS
    absolutely
    1.06
    too
    1.06
    Interstitial
    1.05
    Absolutely
    1.02
    ]'
    0.99
    highly
    0.98
    tis
    0.98
    safe
    0.97
    danger
    0.97
    smart
    0.95
    Activations Density 0.020%

    No Known Activations