© 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 1536
    9. 8-RES_FS1536-JB
    11. 1048
    Prev
    Next
    INDEX
    Explanations

    historical references and political contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.18
    0.8%
    650
    +0.12
    0.6%
    675
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.18
    0.16
    650
    +0.12
    0.16
    333
    +0.11
    0.12
    Negative Logits
     Mirage
    -0.79
     mounts
    -0.69
     reflex
    -0.68
     clitor
    -0.66
     pleasures
    -0.65
     pressures
    -0.64
     vulner
    -0.63
     ways
    -0.63
     Zeit
    -0.63
     lapse
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.33
    ternity
    1.07
    uthor
    0.99
    $
    0.94
    _>
    0.90
    §
    0.89
    ACP
    0.86
    âĶĢâĶĢ
    0.86
    amily
    0.85
    \-
    0.85
    Activations Density 0.730%

    No Known Activations