© 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 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. 10982
    Prev
    Next
    INDEX
    Explanations

    technical information related to mechanical components in a product

    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
    145
    +0.11
    0.5%
    496
    +0.10
    0.4%
    584
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.02
    678
    +0.10
    0.05
    326
    +0.09
    0.05
    Negative Logits
    awatts
    -0.87
    getting
    -0.86
    SPONSORED
    -0.85
    iots
    -0.84
    miss
    -0.83
    Attempts
    -0.82
    dule
    -0.82
    chance
    -0.76
    talk
    -0.76
    someone
    -0.76
    POSITIVE LOGITS
     aluminum
    1.35
     aluminium
    1.30
     stainless
    1.23
     matte
    1.22
     molded
    1.21
     chrome
    1.13
     alloy
    1.13
     Aluminum
    1.11
     silicone
    1.10
     adjustable
    1.09
    Activations Density 0.352%

    No Known Activations