© 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. 37406
    Prev
    Next
    INDEX
    Explanations

    comparative phrases discussing similarities and differences

    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
    365
    +0.11
    0.5%
    514
    +0.10
    0.5%
    292
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.11
    0.02
    11
    +0.10
    0.02
    570
    +0.09
    0.01
    Negative Logits
    stop
    -0.76
    NPR
    -0.67
    watching
    -0.66
     FANTASY
    -0.65
    livion
    -0.65
     responsibly
    -0.64
    retion
    -0.64
     backlog
    -0.63
    nesday
    -0.63
    thouse
    -0.62
    POSITIVE LOGITS
     resemblance
    1.14
     characteristics
    1.11
     similarities
    1.06
     temperament
    0.98
     personalities
    0.97
     resemb
    0.95
     philosophies
    0.94
     similarity
    0.93
     personality
    0.92
     differing
    0.89
    Activations Density 0.150%

    No Known Activations