© 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. 9527
    Prev
    Next
    INDEX
    Explanations

    phrases related to health impacts and risks

    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
    218
    +0.09
    0.4%
    114
    +0.09
    0.4%
    615
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.09
    0.04
    285
    +0.09
    0.03
    225
    +0.09
    0.04
    Negative Logits
    swick
    -0.79
    lio
    -0.67
    ramid
    -0.67
    atters
    -0.67
    Bit
    -0.66
    Blocks
    -0.66
    ership
    -0.65
    bits
    -0.64
    UNCH
    -0.63
     istg
    -0.63
    POSITIVE LOGITS
     outweigh
    1.11
    effects
    1.05
     outwe
    0.97
     incurred
    0.94
     arising
    0.93
     associated
    0.92
     consequences
    0.91
     thereof
    0.90
     inflicted
    0.89
     caused
    0.87
    Activations Density 0.120%

    No Known Activations