© 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. 11955
    Prev
    Next
    INDEX
    Explanations

    descriptions related to travel destinations

    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
    689
    +0.13
    0.6%
    370
    +0.09
    0.4%
    656
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.13
    0.03
    689
    +0.09
    0.04
    641
    +0.09
    0.04
    Negative Logits
    iru
    -0.78
    2020
    -0.75
     2019
    -0.70
     Processor
    -0.69
     2020
    -0.69
    thumbnails
    -0.68
     poses
    -0.66
     2024
    -0.65
     2018
    -0.60
     2030
    -0.60
    POSITIVE LOGITS
     firsthand
    1.13
     experien
    0.89
     countless
    0.87
    ©¶æ
    0.81
     myself
    0.79
    ewitness
    0.77
    etimes
    0.74
     extensively
    0.73
    exper
    0.72
    sbm
    0.71
    Activations Density 0.317%

    No Known Activations