© 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. 8788
    Prev
    Next
    INDEX
    Explanations

    , the main thing this neuron does is find sentences related to health topics and medical conditions

    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
    720
    +0.12
    0.6%
    498
    +0.11
    0.5%
    550
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.12
    0.08
    43
    +0.11
    0.06
    546
    +0.09
    0.06
    Negative Logits
    =#
    -0.58
    "]=>
    -0.55
    ļéĨĴ
    -0.55
    cott
    -0.54
     Respons
    -0.52
     weeds
    -0.51
     Camel
    -0.50
    num
    -0.49
    illion
    -0.49
    robe
    -0.49
    POSITIVE LOGITS
     albeit
    1.14
     moreover
    0.88
     however
    0.87
     alas
    0.86
    albeit
    0.80
     somew
    0.79
     therefore
    0.75
    perhaps
    0.74
     though
    0.74
     notwithstanding
    0.72
    Activations Density 0.303%

    No Known Activations