© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41642
    Prev
    Next
    INDEX
    Explanations

    terms related to educational policies and reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    756
    +0.10
    0.5%
    501
    +0.10
    0.5%
    694
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.07
    314
    +0.10
    0.00
    365
    +0.09
    0.04
    Negative Logits
    ãĤ°
    -0.55
    hematically
    -0.54
     AND
    -0.54
     today
    -0.51
     and
    -0.48
     Aval
    -0.48
     TODAY
    -0.47
     tonight
    -0.47
     Emblem
    -0.46
    ACTED
    -0.46
    POSITIVE LOGITS
     alike
    1.05
     respectively
    0.89
     thereof
    0.85
     thereto
    0.72
     versa
    0.69
     thereafter
    0.67
    depending
    0.59
    ).[
    0.57
    ancel
    0.56
     accordingly
    0.55
    Activations Density 0.530%

    No Known Activations