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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 491
    Prev
    Next
    INDEX
    Explanations

    financial and career-related goals and ambitions

    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
    +0.16
    0.8%
    102
    +0.16
    0.8%
    640
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.16
    0.16
    102
    +0.16
    0.13
    616
    +0.15
    0.12
    Negative Logits
     Cah
    -0.78
     Mermaid
    -0.77
     Phi
    -0.76
     Rica
    -0.75
     Creator
    -0.75
     Wiz
    -0.74
     Richards
    -0.74
     Meadows
    -0.72
     Guru
    -0.71
     Sawyer
    -0.71
    POSITIVE LOGITS
    sized
    1.41
    sounding
    1.37
    bodied
    1.35
    eyed
    1.31
    level
    1.30
    numbered
    1.25
    enough
    1.24
    to
    1.24
    distance
    1.21
    function
    1.21
    Activations Density 0.644%

    No Known Activations