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. 23697
    Prev
    Next
    INDEX
    Explanations

    interactions with images and their functionalities on a website

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.13
    0.6%
    268
    +0.10
    0.4%
    500
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.13
    0.04
    194
    +0.10
    0.03
    268
    +0.09
    0.02
    Negative Logits
     virginity
    -0.77
    livious
    -0.64
    wives
    -0.61
     Stef
    -0.58
    KT
    -0.57
     arson
    -0.56
     dispos
    -0.55
    Ton
    -0.55
    cerned
    -0.53
     Krish
    -0.53
    POSITIVE LOGITS
     thumbnail
    1.02
     IMAGES
    0.93
     bookmark
    0.92
     clicked
    0.91
     slideshow
    0.90
     enlarged
    0.88
     URL
    0.87
     popup
    0.87
    Brow
    0.86
     toolbar
    0.86
    Activations Density 0.259%

    No Known Activations