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 49152
    5. 8-RES_FS49152-JB
    6. 45490
    Prev
    Next
    INDEX
    Explanations

    advocacy for environmental and animal welfare issues

    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
    640
    +0.23
    1.1%
    481
    +0.18
    0.9%
    314
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.07
    160
    +0.18
    0.07
    442
    +0.16
    0.06
    Negative Logits
     lime
    -0.74
     champ
    -0.73
     racer
    -0.73
     tram
    -0.72
     placement
    -0.72
     stomp
    -0.71
     Saiyan
    -0.70
     shelling
    -0.69
     clam
    -0.69
     staging
    -0.69
    POSITIVE LOGITS
    Dear
    1.55
    Introduction
    1.53
    Reviewed
    1.42
    Published
    1.38
    Writing
    1.35
    Written
    1.35
    Chapter
    1.35
    Abstract
    1.35
    Reviewer
    1.33
    Letter
    1.31
    Activations Density 0.114%

    No Known Activations