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 24576
    5. 8-RES_FS24576-JB
    6. 12253
    Prev
    Next
    INDEX
    Explanations

    information about events, promotions, activities, and opportunities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.35
    1.7%
    615
    +0.13
    0.6%
    94
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.13
    94
    +0.13
    0.09
    615
    +0.12
    0.07
    Negative Logits
     imperson
    -0.78
     estranged
    -0.77
     manoeuv
    -0.76
     reversing
    -0.74
     dissu
    -0.73
     footing
    -0.72
    rad
    -0.71
     interference
    -0.70
     acting
    -0.69
     antit
    -0.69
    POSITIVE LOGITS
    Posted
    1.02
    ³³³
    0.93
    Disclaimer
    0.92
    posted
    0.91
    Ingredients
    0.91
    WARNING
    0.89
    FAQ
    0.89
    RESULTS
    0.89
    Bonus
    0.88
    ################################
    0.88
    Activations Density 0.302%

    No Known Activations