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 49152
    5. 8-RES_FS49152-JB
    6. 43184
    Prev
    Next
    INDEX
    Explanations

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    565
    +0.10
    0.5%
    389
    +0.09
    0.4%
    393
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.02
    565
    +0.09
    0.02
    619
    +0.09
    0.02
    Negative Logits
    assembly
    -0.70
    76561
    -0.67
    illus
    -0.63
    assemb
    -0.61
    OST
    -0.60
    Mom
    -0.59
    IT
    -0.59
    Golden
    -0.58
    Jun
    -0.58
    cies
    -0.57
    POSITIVE LOGITS
     be
    1.02
     serve
    1.02
     include
    0.95
     contribute
    0.94
     allow
    0.93
     provide
    0.93
     recognize
    0.92
     contend
    0.91
     incorporate
    0.90
     introduce
    0.90
    Activations Density 0.028%

    No Known Activations