© 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. 8074
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons or contrasts

    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
    574
    +0.12
    0.5%
    15
    +0.10
    0.5%
    764
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.08
    750
    +0.10
    0.04
    408
    +0.10
    0.06
    Negative Logits
    ħĭ
    -0.77
    911
    -0.70
     Earthquake
    -0.69
     Called
    -0.68
    inch
    -0.62
    _(
    -0.62
     Referred
    -0.62
     Higher
    -0.62
     [|
    -0.62
    hirt
    -0.62
    POSITIVE LOGITS
     stuff
    1.19
     crap
    1.16
     goodness
    1.15
     firepower
    1.15
     goodies
    1.10
     chatter
    1.05
     baggage
    1.04
     excitement
    1.00
     fodder
    1.00
     nonsense
    1.00
    Activations Density 0.504%

    No Known Activations