© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37187
    Prev
    Next
    INDEX
    Explanations

    references to ideas or concepts, particularly those that are significant or noteworthy

    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
    659
    +0.10
    0.5%
    220
    +0.10
    0.4%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.10
    0.01
    555
    +0.10
    0.01
    656
    +0.10
    0.01
    Negative Logits
    enegger
    -0.80
    packing
    -0.72
     socks
    -0.70
     Diesel
    -0.69
    lifting
    -0.66
    stakes
    -0.63
     Jagu
    -0.63
     Guinea
    -0.60
     boots
    -0.60
     gluten
    -0.59
    POSITIVE LOGITS
    ologies
    1.08
    ally
    1.07
    OLOG
    1.06
    ality
    1.02
    als
    1.02
    ological
    1.00
    ologue
    0.97
    ative
    0.96
    alis
    0.95
    OLOGY
    0.94
    Activations Density 0.008%

    No Known Activations