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

    Neuronpedia

    Jacobian LensNEW
    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. 10847
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations

    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
    114
    +0.12
    0.5%
    668
    +0.11
    0.5%
    145
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.12
    0.03
    668
    +0.11
    0.03
    6
    +0.10
    0.04
    Negative Logits
    Pri
    -0.67
    changes
    -0.66
    eatures
    -0.62
    cation
    -0.62
    Object
    -0.62
    reason
    -0.60
    isations
    -0.58
    stream
    -0.57
    ãĥ´ãĤ¡
    -0.57
     convol
    -0.57
    POSITIVE LOGITS
     guiActiveUn
    0.90
     âĵĺ
    0.87
     âĨij
    0.86
     âĨĴ
    0.84
     Leilan
    0.82
     [+]
    0.79
     +++
    0.78
    EStream
    0.77
     sshd
    0.76
     CrossRef
    0.75
    Activations Density 0.111%

    No Known Activations