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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 11935
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and negative comparisons

    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
    152
    +0.12
    0.6%
    460
    +0.11
    0.5%
    378
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.12
    0.04
    425
    +0.11
    0.03
    460
    +0.09
    0.03
    Negative Logits
    Ń·
    -0.67
    aiman
    -0.66
    estern
    -0.63
     Richards
    -0.63
    pload
    -0.61
     Restrict
    -0.60
     SOL
    -0.59
    EStream
    -0.58
    EMENT
    -0.56
     Shutterstock
    -0.56
    POSITIVE LOGITS
    degree
    1.22
    century
    1.20
    generation
    1.15
    tier
    1.11
    favorite
    1.07
    ranked
    1.04
    rate
    1.03
    dimensional
    1.03
    highest
    1.01
    party
    1.00
    Activations Density 0.029%

    No Known Activations