© 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. 19409
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and controversies

    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
    447
    +0.17
    0.8%
    481
    +0.11
    0.5%
    241
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.17
    0.07
    51
    +0.11
    0.05
    567
    +0.11
    0.04
    Negative Logits
    SPONSORED
    -0.81
    Oracle
    -0.69
    rawdownloadcloneembedreportprint
    -0.67
    cer
    -0.66
    UCK
    -0.65
    ATIONAL
    -0.64
     Ladies
    -0.62
    LECT
    -0.61
    EDIT
    -0.61
    CONCLUS
    -0.60
    POSITIVE LOGITS
    hips
    0.92
     fleeing
    0.91
    hip
    0.88
     who
    0.85
    '
    0.84
    paces
    0.83
    pread
    0.83
     harmed
    0.82
    ongs
    0.80
    afety
    0.79
    Activations Density 0.252%

    No Known Activations