© 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. 8148
    Prev
    Next
    INDEX
    Explanations

    mentions of the company Enron and related financial scandals

    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
    481
    +0.37
    1.8%
    447
    +0.14
    0.7%
    430
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.37
    0.05
    659
    +0.14
    0.05
    404
    +0.13
    0.04
    Negative Logits
    ongyang
    -0.67
    drm
    -0.66
    atform
    -0.60
     inver
    -0.58
    ymph
    -0.58
     Seym
    -0.58
    stream
    -0.57
     Euph
    -0.54
    config
    -0.52
    wcsstore
    -0.51
    POSITIVE LOGITS
     Lauder
    0.86
    issance
    0.84
    xual
    0.75
    ciating
    0.72
     Abbey
    0.71
    cia
    0.68
    ion
    0.66
    enment
    0.65
    ction
    0.63
     Cathedral
    0.62
    Activations Density 0.319%

    No Known Activations