© 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 49152
    9. 8-RES_FS49152-JB
    11. 26804
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in" to indicate trends or locations within contexts related to analysis or reporting

    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
    314
    +0.15
    0.7%
    123
    +0.12
    0.6%
    300
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.15
    0.07
    22
    +0.12
    0.06
    257
    +0.12
    0.05
    Negative Logits
    tein
    -0.70
    tre
    -0.68
    wine
    -0.67
    tar
    -0.66
    romeda
    -0.65
    pez
    -0.64
    atel
    -0.62
     ingred
    -0.62
     datas
    -0.61
    poon
    -0.61
    POSITIVE LOGITS
     terms
    1.08
     regards
    1.07
     spite
    0.94
    efficiency
    0.93
    effic
    0.91
    herent
    0.87
    ordinate
    0.87
     nutshell
    0.86
    clus
    0.85
     Australia
    0.85
    Activations Density 0.206%

    No Known Activations