© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    references to technological terms, especially related to software development and cyber security

    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
    0
    +0.12
    0.6%
    290
    +0.10
    0.5%
    65
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.12
    0.02
    626
    +0.10
    0.01
    0
    +0.10
    0.02
    Negative Logits
    owicz
    -0.69
    braska
    -0.62
     orche
    -0.62
    etheless
    -0.60
    theless
    -0.59
    ogene
    -0.59
    lessness
    -0.59
     obst
    -0.58
     transit
    -0.58
     aur
    -0.57
    POSITIVE LOGITS
    Cs
    1.05
    HI
    1.00
    Bs
    0.97
    RD
    0.89
    CT
    0.89
    RT
    0.87
    BG
    0.85
    Ds
    0.85
    Vs
    0.82
    ¹
    0.81
    Activations Density 0.008%

    No Known Activations