© 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. 12065
    Prev
    Next
    INDEX
    Explanations

    terms related to databases and data management

    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
    24
    +0.11
    0.5%
    639
    +0.10
    0.5%
    610
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.11
    0.03
    767
    +0.10
    0.03
    373
    +0.10
    -0.01
    Negative Logits
     Christensen
    -0.66
     Balt
    -0.63
     Bened
    -0.60
     McDonnell
    -0.59
     ironic
    -0.58
     Levi
    -0.57
     Leh
    -0.56
     failing
    -0.56
     Carnegie
    -0.56
     blame
    -0.56
    POSITIVE LOGITS
    acteria
    1.01
    oard
    1.00
    urger
    0.99
    augh
    0.96
    ecause
    0.93
    udd
    0.87
    odies
    0.87
    iotics
    0.86
    rew
    0.86
    ilk
    0.82
    Activations Density 0.045%

    No Known Activations