© 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. 19613
    Prev
    Next
    INDEX
    Explanations

    phrases related to public speeches and crowd reactions

    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
    447
    +0.12
    0.5%
    481
    +0.10
    0.5%
    106
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.12
    0.02
    106
    +0.10
    0.03
    168
    +0.09
    0.03
    Negative Logits
     Copy
    -0.71
     situational
    -0.69
    trade
    -0.69
     Ide
    -0.69
    Travel
    -0.68
    iasis
    -0.66
    omal
    -0.66
     Equip
    -0.65
     Dating
    -0.65
    erenn
    -0.64
    POSITIVE LOGITS
     cheering
    1.30
     cheers
    1.21
     applause
    1.18
     attendees
    1.10
     chanting
    1.10
     cheered
    1.08
     applaud
    1.05
     gasped
    1.04
     gathered
    1.02
     roared
    1.01
    Activations Density 0.129%

    No Known Activations