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. 1352
    Prev
    Next
    INDEX
    Explanations

    phrases related to military conflicts

    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
    288
    +0.15
    0.7%
    150
    +0.10
    0.5%
    531
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.13
    531
    +0.10
    0.08
    444
    +0.10
    0.07
    Negative Logits
    Asset
    -0.75
    */(
    -0.70
     Thumbnails
    -0.70
    OGR
    -0.69
    ource
    -0.66
    ITY
    -0.66
    essee
    -0.63
     drawer
    -0.62
     Seller
    -0.62
    ity
    -0.61
    POSITIVE LOGITS
    lord
    1.29
    lords
    1.27
    fare
    1.27
    rior
    1.25
    riors
    1.22
    fighter
    1.02
    hammer
    1.01
    ring
    0.98
     waged
    0.96
    bler
    0.95
    Activations Density 1.827%

    No Known Activations