© 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. 2705
    Prev
    Next
    INDEX
    Explanations

    statements by individuals expressing personal beliefs or convictions

    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
    718
    +0.13
    0.6%
    93
    +0.13
    0.6%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.13
    0.09
    566
    +0.13
    0.09
    93
    +0.10
    0.09
    Negative Logits
     Vin
    -0.70
     OG
    -0.65
     Mig
    -0.64
     Vie
    -0.63
     Takeru
    -0.62
     Rolls
    -0.59
     Gap
    -0.59
     Semi
    -0.58
    Mech
    -0.57
     Weird
    -0.57
    POSITIVE LOGITS
    'm
    1.36
     personally
    1.15
     am
    1.14
    've
    1.09
     hereby
    1.06
     commend
    1.06
     sincerely
    1.05
     apologise
    1.04
     congratulate
    1.04
     respectfully
    1.03
    Activations Density 0.246%

    No Known Activations