© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or services to specific groups of people

    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
    224
    +0.10
    0.4%
    354
    +0.10
    0.4%
    225
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.10
    0.04
    492
    +0.10
    0.04
    139
    +0.10
    0.04
    Negative Logits
     intervening
    -0.59
    iHUD
    -0.58
     Chou
    -0.58
     Roose
    -0.57
     surve
    -0.57
     branch
    -0.56
     Torrent
    -0.56
     relent
    -0.56
     BCC
    -0.55
     DOT
    -0.55
    POSITIVE LOGITS
    needed
    1.11
     deserved
    1.03
     needed
    0.95
     desired
    0.91
    Ĥİ
    0.88
     sorely
    0.88
     normally
    0.85
     deserve
    0.84
    ļé
    0.84
     rightfully
    0.82
    Activations Density 0.133%

    No Known Activations