© 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. 18687
    Prev
    Next
    INDEX
    Explanations

    text related to absence or lack of something

    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
    36
    +0.21
    1.0%
    393
    +0.17
    0.8%
    263
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.21
    0.10
    636
    +0.17
    0.05
    263
    +0.11
    0.05
    Negative Logits
    almost
    -0.73
    Links
    -0.70
    assisted
    -0.69
    Contents
    -0.67
    alian
    -0.67
    AUD
    -0.67
    unknown
    -0.66
    Mis
    -0.66
    bec
    -0.66
    Inf
    -0.65
    POSITIVE LOGITS
     dime
    1.20
     satisfactory
    1.13
     lot
    1.12
     clue
    1.12
     single
    1.06
     definitive
    1.01
     slightest
    1.00
     meaningful
    0.99
     coherent
    0.98
     cohesive
    0.96
    Activations Density 0.168%

    No Known Activations