© 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. 12177
    Prev
    Next
    INDEX
    Explanations

    sentences containing reflections or insights prompting people to be mindful or learn from a given situation

    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
    354
    +0.11
    0.5%
    730
    +0.10
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.11
    0.01
    354
    +0.10
    0.01
    417
    +0.10
    0.01
    Negative Logits
    apor
    -0.74
    quer
    -0.72
    anova
    -0.71
    abases
    -0.71
    quire
    -0.69
    76561
    -0.69
    á
    -0.66
    yna
    -0.66
    iets
    -0.65
    artney
    -0.64
    POSITIVE LOGITS
     reminder
    1.04
     reminders
    1.02
     remind
    0.85
     reminding
    0.81
     vigilance
    0.78
    llor
    0.74
    fulness
    0.71
     refreshed
    0.69
    emonic
    0.68
    reader
    0.68
    Activations Density 0.014%

    No Known Activations