© 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. 250
    Prev
    Next
    INDEX
    Explanations

    the word "monolithic."

    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
    640
    +0.11
    0.5%
    314
    +0.11
    0.5%
    31
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.11
    0.02
    421
    +0.11
    0.02
    52
    +0.10
    0.02
    Negative Logits
     Norn
    -0.89
    ORTS
    -0.76
    INGTON
    -0.75
    FUL
    -0.74
    IBLE
    -0.72
    ATOR
    -0.71
     enrichment
    -0.68
    ULTS
    -0.67
     Venom
    -0.67
    UGE
    -0.65
    POSITIVE LOGITS
    stros
    1.42
    olithic
    1.35
    olith
    1.33
    soon
    1.25
    ograph
    1.23
    ographs
    1.18
    oton
    1.15
    ocular
    1.14
    ologue
    1.11
    itored
    1.07
    Activations Density 0.014%

    No Known Activations