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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1043
    Prev
    Next
    INDEX
    Explanations

    information related to military ships and incidents at sea

    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
    +0.22
    1.0%
    640
    +0.13
    0.6%
    152
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.22
    0.14
    314
    +0.13
    0.04
    537
    +0.11
    0.12
    Negative Logits
     ballpark
    -0.72
     Dickinson
    -0.71
     interval
    -0.70
     zip
    -0.69
     caution
    -0.69
     square
    -0.68
     drawer
    -0.68
     hiber
    -0.68
     displays
    -0.68
     showers
    -0.67
    POSITIVE LOGITS
    style
    1.60
    based
    1.58
    inspired
    1.56
    induced
    1.54
    derived
    1.50
    themed
    1.49
    sized
    1.47
    esque
    1.42
    related
    1.41
    sama
    1.38
    Activations Density 0.734%

    No Known Activations