© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and events occurring over time

    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
    393
    +0.15
    0.7%
    362
    +0.14
    0.7%
    640
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.08
    475
    +0.14
    0.05
    385
    +0.13
    0.06
    Negative Logits
    itiz
    -0.79
    ional
    -0.68
    irds
    -0.68
     owes
    -0.65
    #$
    -0.64
     owed
    -0.60
    Topics
    -0.60
    abe
    -0.59
     malf
    -0.59
    uty
    -0.58
    POSITIVE LOGITS
     meantime
    1.65
     midst
    1.30
     absence
    1.24
     aftermath
    1.21
     simplest
    1.08
     context
    1.05
     nutshell
    1.02
     guise
    0.99
     ensuing
    0.97
     case
    0.96
    Activations Density 0.230%

    No Known Activations