© 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. 8512
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments, specifically focusing on the term "ophthalmology."

    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
    128
    +0.12
    0.5%
    461
    +0.09
    0.4%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.12
    0.01
    738
    +0.09
    0.01
    128
    +0.09
    0.01
    Negative Logits
    forth
    -0.77
    LOAD
    -0.69
    WARD
    -0.68
     Progressive
    -0.64
     wont
    -0.64
    âĸ¬âĸ¬
    -0.64
     compuls
    -0.63
    FIN
    -0.63
    nels
    -0.61
    PUT
    -0.59
    POSITIVE LOGITS
    osph
    1.34
    osate
    1.33
    ouse
    1.18
    ilia
    1.13
    ysics
    1.12
    ouses
    1.12
    ilic
    1.12
    obe
    1.08
    iles
    1.06
    rase
    1.03
    Activations Density 0.016%

    No Known Activations