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. 789
    Prev
    Next
    INDEX
    Explanations

    words related to advertisements and marketing strategies

    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
    +0.11
    0.5%
    578
    +0.11
    0.5%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.15
    641
    +0.11
    0.09
    247
    +0.11
    0.06
    Negative Logits
    claw
    -0.74
     Templar
    -0.72
    Jr
    -0.69
    borg
    -0.67
     Carbuncle
    -0.66
     TAMADRA
    -0.65
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    essional
    -0.64
    lihood
    -0.64
    iciary
    -0.64
    POSITIVE LOGITS
    vertising
    1.02
     campaigns
    1.01
     advertising
    0.94
    verts
    0.92
     banners
    0.88
     blitz
    0.88
     slogan
    0.85
     billboards
    0.84
     Advertising
    0.83
     campaign
    0.81
    Activations Density 2.779%

    No Known Activations