© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 2065
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and outcomes

    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
    288
    +0.12
    0.5%
    561
    +0.10
    0.5%
    311
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.12
    0.02
    79
    +0.10
    0.02
    561
    +0.10
    0.02
    Negative Logits
    drops
    -0.76
    zik
    -0.70
    trap
    -0.67
    jar
    -0.66
    wic
    -0.66
    atra
    -0.66
    steps
    -0.64
    eper
    -0.64
     capped
    -0.64
    uty
    -0.64
    POSITIVE LOGITS
     fiction
    1.02
     literacy
    1.01
     curiosity
    1.01
     research
    0.90
     misconduct
    0.89
    ĨĴ
    0.86
     inquiry
    0.86
     endeavors
    0.85
     discoveries
    0.83
     advisory
    0.83
    Activations Density 0.026%

    No Known Activations