© 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. 12138
    Prev
    Next
    INDEX
    Explanations

    emotional language and expressions related to praise or criticism

    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
    514
    +0.11
    0.5%
    174
    +0.10
    0.5%
    604
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.06
    514
    +0.10
    0.04
    734
    +0.10
    0.04
    Negative Logits
     è£ıè
    -0.74
    uyomi
    -0.69
    ACP
    -0.67
    thodox
    -0.66
    ãĥ¼ãĥĨ
    -0.65
    é¾įå¥ij士
    -0.65
    Struct
    -0.62
    Eastern
    -0.60
    PF
    -0.59
    gd
    -0.59
    POSITIVE LOGITS
     yourselves
    1.59
     yourself
    1.20
    Tube
    0.86
     your
    0.84
    your
    0.81
     YOUR
    0.75
     Yourself
    0.75
     majesty
    0.73
     cunt
    0.73
     sir
    0.72
    Activations Density 0.284%

    No Known Activations