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 3072
    5. 8-RES_FS3072-JB
    6. 1001
    Prev
    Next
    INDEX
    Explanations

    information related to medical research and scientific findings on the effects of certain interventions on biological processes or symptoms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    239
    +0.10
    0.4%
    368
    +0.10
    0.4%
    156
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.10
    0.07
    239
    +0.10
    0.06
    686
    +0.09
    0.05
    Negative Logits
    soDeliveryDate
    -0.80
     Armageddon
    -0.77
     brim
    -0.77
     yours
    -0.75
    Revolution
    -0.74
     lett
    -0.72
    kos
    -0.69
     sails
    -0.69
    terday
    -0.68
    biz
    -0.67
    POSITIVE LOGITS
     âμ
    1.30
     biomark
    1.28
     (âĪĴ
    1.27
     phenotype
    1.27
     allele
    1.20
     susceptibility
    1.19
     β
    1.19
     clinically
    1.18
     correlated
    1.16
     antidepressant
    1.15
    Activations Density 2.681%

    No Known Activations