© 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 EvalsExportsinterp-engineNEWAPI 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. 2341
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural disasters and climate change, particularly focusing on severe weather events and their impacts

    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
    157
    +0.10
    0.4%
    373
    +0.09
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.10
    0.01
    373
    +0.09
    -0.01
    406
    +0.09
    0.01
    Negative Logits
    arella
    -0.72
    natureconservancy
    -0.66
    atorium
    -0.62
     Blink
    -0.55
    ISO
    -0.55
    URI
    -0.55
    003
    -0.54
     blur
    -0.54
    ULT
    -0.54
    ãģ®å
    -0.54
    POSITIVE LOGITS
    thood
    1.27
    ts
    1.18
    sburg
    1.07
    sis
    1.03
    tics
    0.99
    nce
    0.98
    tes
    0.98
    cies
    0.97
    ty
    0.93
    tyard
    0.92
    Activations Density 0.030%

    No Known Activations