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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 918
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to medical effects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    420
    +0.15
    0.7%
    558
    +0.11
    0.5%
    220
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.15
    0.08
    420
    +0.11
    0.10
    558
    +0.10
    0.09
    Negative Logits
    inventoryQuantity
    -0.80
    edin
    -0.72
    aretz
    -0.71
    thora
    -0.68
    Jar
    -0.64
    Dad
    -0.64
    daq
    -0.63
     Ranger
    -0.62
    BuyableInstoreAndOnline
    -0.62
    EStream
    -0.60
    POSITIVE LOGITS
     abbre
    1.10
     acronym
    1.09
     loosely
    1.03
     combining
    0.93
     shorthand
    0.93
    quartered
    0.92
     specialized
    0.87
     coined
    0.84
     comprised
    0.84
     grouping
    0.83
    Activations Density 3.903%

    No Known Activations