© 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. 19412
    Prev
    Next
    INDEX
    Explanations

    expressions indicating desire or necessity

    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
    728
    +0.12
    0.5%
    737
    +0.12
    0.5%
    570
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.12
    0.02
    119
    +0.12
    0.04
    728
    +0.11
    0.03
    Negative Logits
    LET
    -0.77
    updated
    -0.76
    BLIC
    -0.71
    icum
    -0.71
    Bridge
    -0.70
    olicited
    -0.68
    Edited
    -0.66
    ENTION
    -0.64
    EDIT
    -0.64
    ELS
    -0.64
    POSITIVE LOGITS
     yourself
    1.32
     yourselves
    1.16
     somebody
    0.83
     your
    0.82
     guys
    0.81
     kidding
    0.74
     oneself
    0.74
     extremes
    0.69
     Yourself
    0.67
     pudding
    0.67
    Activations Density 0.339%

    No Known Activations