© 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 49152
    9. 8-RES_FS49152-JB
    11. 26697
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional expressions or sentiments in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    273
    +0.12
    0.5%
    59
    +0.10
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.05
    380
    +0.10
    0.04
    546
    +0.10
    0.04
    Negative Logits
    ãĤ´ãĥ³
    -0.95
    interstitial
    -0.81
     guiActiveUn
    -0.74
    Detailed
    -0.70
    MpServer
    -0.69
    ELD
    -0.68
    osponsors
    -0.67
    Requirements
    -0.67
     âĢº
    -0.67
    Associated
    -0.66
    POSITIVE LOGITS
     however
    1.49
     though
    1.26
     meanwhile
    1.25
     moreover
    1.24
     anyway
    0.99
     somew
    0.98
     yeah
    0.97
     tho
    0.93
     yes
    0.92
     nobody
    0.92
    Activations Density 0.198%

    No Known Activations