© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    keywords related to weaponry and technology

    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
    463
    +0.12
    0.5%
    751
    +0.10
    0.5%
    553
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.12
    0.03
    516
    +0.10
    0.02
    751
    +0.10
    0.02
    Negative Logits
     Sound
    -0.71
    ween
    -0.69
    Mos
    -0.67
     Vide
    -0.66
    mitting
    -0.61
     Dough
    -0.61
    Pass
    -0.60
    lucent
    -0.60
    due
    -0.60
    LOAD
    -0.60
    POSITIVE LOGITS
    chair
    1.50
    ament
    1.50
    aments
    1.50
    ageddon
    1.38
    chairs
    1.21
    atures
    1.19
    ature
    1.14
    amental
    1.05
    ando
    1.04
    orers
    1.01
    Activations Density 0.073%

    No Known Activations