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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1214
    Prev
    Next
    INDEX
    Explanations

    information related to the entertainment industry

    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
    87
    +0.33
    2.0%
    459
    +0.14
    0.8%
    0
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.33
    -0.07
    459
    +0.14
    0.12
    15
    +0.09
    0.13
    Negative Logits
     UNCLASSIFIED
    -0.81
     skelet
    -0.67
     Azerb
    -0.59
    âķIJ
    -0.59
     pse
    -0.58
    etheless
    -0.58
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.57
    âĹ¼
    -0.57
     exting
    -0.56
     cryst
    -0.56
    POSITIVE LOGITS
     âĢİ
    0.69
     âĢº
    0.63
     [â̦]
    0.61
     Donald
    0.61
    âĢİ
    0.60
     frontman
    0.54
     Belfast
    0.53
     Posted
    0.53
    WASHINGTON
    0.50
    Welcome
    0.49
    Activations Density 5.969%

    No Known Activations