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. 524
    Prev
    Next
    INDEX
    Explanations

    text related to media playback issues on devices

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    +0.20
    0.9%
    230
    +0.11
    0.5%
    121
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.20
    0.02
    121
    +0.11
    0.01
    746
    +0.10
    0.01
    Negative Logits
     mete
    -0.68
     recl
    -0.65
     shrew
    -0.65
     nib
    -0.62
    omics
    -0.60
     nig
    -0.60
    aunder
    -0.60
    naire
    -0.60
     sed
    -0.59
    bats
    -0.59
    POSITIVE LOGITS
    UTERS
    0.76
     WATCH
    0.75
     caption
    0.74
     Provided
    0.72
    taboola
    0.70
     Videos
    0.68
    gallery
    0.68
    âĹ¼
    0.67
    :/
    0.66
    ÙĬ
    0.66
    Activations Density 0.005%

    No Known Activations