© 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. 5998
    Prev
    Next
    INDEX
    Explanations

    mentions of human rights violations and related issues

    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
    332
    +0.12
    0.5%
    515
    +0.12
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.04
    515
    +0.12
    0.04
    719
    +0.11
    0.03
    Negative Logits
     Transcript
    -0.77
    forth
    -0.70
    onne
    -0.69
    RET
    -0.65
     Gunn
    -0.64
     Elijah
    -0.64
    urations
    -0.61
     Rowling
    -0.61
     buckle
    -0.61
     WARNING
    -0.60
    POSITIVE LOGITS
    itarian
    1.39
    itar
    1.26
     beings
    1.17
    itary
    1.11
    istic
    1.03
     rights
    1.03
     Rights
    0.98
    rights
    0.98
     trafficking
    0.94
    oids
    0.93
    Activations Density 0.025%

    No Known Activations