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 1536
    5. 8-RES_FS1536-JB
    6. 1189
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and strategy

    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
    373
    +0.16
    0.7%
    659
    +0.11
    0.5%
    716
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.16
    0.10
    298
    +0.11
    0.07
    207
    +0.11
    0.06
    Negative Logits
    blem
    -0.62
    blems
    -0.59
    Adapt
    -0.58
    Continue
    -0.58
    ulner
    -0.57
    needed
    -0.57
     TAMADRA
    -0.56
    ogie
    -0.56
    ocument
    -0.55
    Ore
    -0.54
    POSITIVE LOGITS
     standpoint
    1.77
     vantage
    1.45
     perspective
    1.38
     onwards
    1.30
     outset
    1.30
     perspectives
    1.06
     viewpoint
    1.05
    ratch
    1.01
     onward
    1.00
     mouths
    0.97
    Activations Density 2.226%

    No Known Activations