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 49152
    5. 8-RES_FS49152-JB
    6. 41363
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Frances."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    35
    +0.11
    0.5%
    430
    +0.09
    0.4%
    730
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.11
    0.01
    141
    +0.09
    0.01
    236
    +0.09
    0.01
    Negative Logits
     sockets
    -0.76
    ocrine
    -0.66
     Helsinki
    -0.66
    uyomi
    -0.63
     expectancy
    -0.62
     modernization
    -0.62
    igation
    -0.61
    ansas
    -0.60
    akings
    -0.60
    yrinth
    -0.59
    POSITIVE LOGITS
    ca
    1.07
    olini
    1.00
    chi
    0.96
    chini
    0.96
    co
    0.94
    terness
    0.91
    quin
    0.90
    chal
    0.90
    etta
    0.89
    coni
    0.89
    Activations Density 0.005%

    No Known Activations