Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1052
    Prev
    Next
    INDEX
    Explanations

    medical conditions or related terms with a focus on hypoglycemia

    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
    494
    +0.13
    0.6%
    240
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.01
    355
    +0.11
    0.01
    699
    +0.10
    0.01
    Negative Logits
    holder
    -0.87
    Reloaded
    -0.67
     Bers
    -0.66
    FORE
    -0.65
    âĹ¼
    -0.65
    ãģ®éŃĶ
    -0.64
    å§«
    -0.64
     Empires
    -0.63
    Accessory
    -0.63
    د
    -0.63
    POSITIVE LOGITS
    oxic
    1.15
    nosis
    1.14
    ochond
    1.07
    ohyd
    1.02
    ogly
    1.00
    emic
    0.99
    ocaust
    0.98
    etr
    0.95
    othes
    0.95
    lex
    0.94
    Activations Density 0.011%

    No Known Activations