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. 778
    Prev
    Next
    INDEX
    Explanations

    political and governmental discussions and controversies

    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
    314
    +0.11
    0.5%
    333
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.12
    333
    +0.10
    0.11
    168
    +0.10
    0.11
    Negative Logits
     incorpor
    -0.92
     manif
    -0.77
     levers
    -0.77
     ropes
    -0.77
     appropri
    -0.75
     synerg
    -0.75
     slic
    -0.74
     machines
    -0.73
     tides
    -0.73
     reflex
    -0.73
    POSITIVE LOGITS
    ï¸ı
    1.49
    âĶĢâĶĢ
    1.25
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.10
    âĶĢâĶĢâĶĢâĶĢ
    0.98
    âĹ
    0.92
    âĸ¬âĸ¬
    0.89
    ï¸
    0.88
     Edited
    0.84
    âĢ
    0.83
    ×Ķ
    0.83
    Activations Density 0.612%

    No Known Activations