© 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 EvalsExportsinterp-engineNEWAPI 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. 2837
    Prev
    Next
    INDEX
    Explanations

    decimals indicating mathematical operations, code syntax, and descriptions related to technical 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
    480
    +0.43
    2.3%
    420
    +0.10
    0.5%
    399
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    -0.00
    351
    +0.10
    0.04
    665
    +0.09
    0.07
    Negative Logits
     Keys
    -0.49
     publicity
    -0.48
     Sochi
    -0.47
     partnerships
    -0.46
     Kickstarter
    -0.46
     Insp
    -0.46
     collaboration
    -0.46
     research
    -0.46
     collaborations
    -0.45
    ibe
    -0.45
    POSITIVE LOGITS
     indistinguishable
    0.84
    etheless
    0.66
     considerably
    0.66
     MUCH
    0.64
     anew
    0.61
     indist
    0.60
     progressively
    0.60
     virtually
    0.59
     quite
    0.59
    emin
    0.58
    Activations Density 1.193%

    No Known Activations