© 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. 12020
    Prev
    Next
    INDEX
    Explanations

    instances of personal decisions or opinions in text

    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
    87
    +0.27
    1.3%
    95
    +0.10
    0.5%
    579
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.27
    -0.03
    411
    +0.10
    0.05
    762
    +0.09
    0.08
    Negative Logits
     themselves
    -0.68
     respectively
    -0.64
    Their
    -0.60
    their
    -0.59
    EMS
    -0.55
     Autob
    -0.55
     alike
    -0.54
     allegedly
    -0.54
     Their
    -0.54
     their
    -0.53
    POSITIVE LOGITS
     myself
    1.54
     my
    0.91
    poke
    0.72
    ograp
    0.64
     personally
    0.61
     fuckin
    0.61
    chair
    0.58
     MY
    0.58
    milo
    0.57
    laughs
    0.56
    Activations Density 0.896%

    No Known Activations