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. 10979
    Prev
    Next
    INDEX
    Explanations

    aspects or elements related to legislation, government decisions, law enforcement, and regulations

    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
    348
    +0.10
    0.5%
    273
    +0.10
    0.4%
    752
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.10
    0.02
    348
    +0.10
    0.02
    657
    +0.09
    0.02
    Negative Logits
     slightest
    -0.71
     clipboard
    -0.66
    avorite
    -0.63
    htaking
    -0.61
    continue
    -0.60
     favourite
    -0.60
    onut
    -0.59
     NEXT
    -0.59
    nder
    -0.58
     haun
    -0.57
    POSITIVE LOGITS
    lie
    0.67
    catentry
    0.66
     thanks
    0.65
    urer
    0.63
    ridge
    0.63
    eston
    0.62
     due
    0.62
    spring
    0.62
    meal
    0.62
     relying
    0.62
    Activations Density 0.023%

    No Known Activations