© 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. 12062
    Prev
    Next
    INDEX
    Explanations

    the word 'let'

    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
    283
    +0.09
    0.4%
    191
    +0.09
    0.4%
    356
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.09
    0.03
    131
    +0.09
    0.03
    108
    +0.09
    0.03
    Negative Logits
    natureconservancy
    -0.70
    MODE
    -0.69
     cumbers
    -0.60
    Zen
    -0.59
    omething
    -0.58
     agre
    -0.58
    BLE
    -0.57
    ombat
    -0.55
    iege
    -0.55
    ource
    -0.55
    POSITIVE LOGITS
    tered
    1.10
    icia
    1.00
    itia
    1.00
    ting
    0.97
    tering
    0.92
    downs
    0.78
    hetically
    0.78
    ugal
    0.75
    inous
    0.71
    ingly
    0.71
    Activations Density 0.025%

    No Known Activations