© 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. 45570
    Prev
    Next
    INDEX
    Explanations

    decimal points or version numbers in software updates

    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
    640
    +0.14
    0.7%
    314
    +0.11
    0.5%
    601
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.14
    0.02
    137
    +0.11
    0.01
    197
    +0.11
    0.01
    Negative Logits
     affili
    -0.76
     deliber
    -0.75
     mislead
    -0.70
     embell
    -0.66
     indo
    -0.66
     thr
    -0.65
     offic
    -0.64
     boycot
    -0.64
     deduct
    -0.64
     fallacy
    -0.63
    POSITIVE LOGITS
    dylib
    1.15
    0
    0.99
    jar
    0.94
    gz
    0.94
    jpg
    0.93
    7601
    0.92
    840
    0.90
    1
    0.88
    zip
    0.88
    compatible
    0.84
    Activations Density 0.020%

    No Known Activations