© 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 EvalsExportsinterp-engineNEWAPI 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. 2564
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a small or specific quantity 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
    19
    +0.10
    0.5%
    313
    +0.10
    0.5%
    625
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    625
    +0.10
    0.04
    313
    +0.10
    0.04
    8
    +0.10
    0.04
    Negative Logits
     agre
    -0.76
    acus
    -0.74
    yrinth
    -0.71
    andise
    -0.71
     conclud
    -0.68
    sein
    -0.67
    alam
    -0.67
    claimed
    -0.64
    akings
    -0.64
     thence
    -0.64
    POSITIVE LOGITS
     hundred
    1.54
     dozen
    1.53
     thousand
    1.38
     weeks
    1.18
     minutes
    1.07
     months
    1.06
    dozen
    1.06
     days
    1.05
     moments
    1.01
     seconds
    0.99
    Activations Density 0.059%

    No Known Activations