© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10498
    Prev
    Next
    INDEX
    Explanations

    uniquely numbered sequences in a structured format

    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
    600
    +0.12
    0.5%
    297
    +0.11
    0.5%
    365
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.12
    0.02
    383
    +0.11
    0.02
    2
    +0.10
    0.01
    Negative Logits
     amen
    -0.75
     VO
    -0.72
     mosqu
    -0.72
     365
    -0.68
     Map
    -0.66
     MAP
    -0.64
     ENG
    -0.64
     endorsements
    -0.64
     IMP
    -0.63
     ko
    -0.63
    POSITIVE LOGITS
    th
    1.82
    rd
    1.56
    ths
    1.51
    nd
    1.33
    inth
    1.28
    eenth
    1.24
    TH
    1.23
    venth
    1.23
    teenth
    1.23
    st
    1.18
    Activations Density 0.041%

    No Known Activations