© 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 12288
    9. 8-RES_FS12288-JB
    11. 10663
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms or terms related to academic subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.53
    3.4%
    87
    +0.41
    2.7%
    266
    +0.20
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.53
    0.12
    480
    +0.41
    0.05
    232
    +0.20
    0.10
    Negative Logits
     destro
    -0.59
    enegger
    -0.56
     undermin
    -0.52
    Interstitial
    -0.52
     helicop
    -0.51
     disadvant
    -0.50
     therein
    -0.48
     beforehand
    -0.48
     conclud
    -0.48
     Peb
    -0.48
    POSITIVE LOGITS
    \":
    0.52
    ĭ
    0.49
    Äģ
    0.48
    ®
    0.47
    ļ
    0.47
    §
    0.46
    amins
    0.46
    asing
    0.45
    º
    0.45
     âĢº
    0.45
    Activations Density 1.247%

    No Known Activations