Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11398
    Prev
    Next
    INDEX
    Explanations

    words related to history and human 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_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
    87
    +0.17
    0.8%
    459
    +0.12
    0.6%
    464
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.17
    0.06
    459
    +0.12
    0.07
    756
    +0.12
    -0.02
    Negative Logits
    -+-+
    -0.68
     stru
    -0.58
     seiz
    -0.55
    iatus
    -0.54
     disg
    -0.54
     fundament
    -0.53
     disapp
    -0.52
     arrang
    -0.52
    enos
    -0.51
     Wik
    -0.51
    POSITIVE LOGITS
    idge
    0.72
    éĥ
    0.68
    oliath
    0.65
    èĥ
    0.62
    wen
    0.62
     likewise
    0.61
    numbered
    0.61
    erning
    0.59
    itudes
    0.58
    ãģ®é
    0.58
    Activations Density 1.080%

    No Known Activations