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. 1328
    Prev
    Next
    INDEX
    Explanations

    statements related to political ideologies and debates

    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
    640
    +0.21
    1.0%
    6
    +0.15
    0.7%
    481
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.27
    6
    +0.15
    0.22
    64
    +0.14
    -0.08
    Negative Logits
     undet
    -0.77
     fused
    -0.75
    cffff
    -0.75
     indu
    -0.70
     conscious
    -0.69
     endeav
    -0.68
     shuff
    -0.67
     honoured
    -0.67
    icter
    -0.67
     centrally
    -0.66
    POSITIVE LOGITS
    Indeed
    1.22
    Refer
    1.19
    RAW
    1.15
    =-=-=-=-=-=-=-=-
    1.15
    Comment
    1.12
    Regarding
    1.10
    CONCLUS
    1.09
    Asked
    1.08
    Translation
    1.07
    Another
    1.06
    Activations Density 2.175%

    No Known Activations