© 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. 26693
    Prev
    Next
    INDEX
    Explanations

    references to financial limitations and factors related to economics

    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
    447
    +0.20
    1.0%
    756
    +0.16
    0.8%
    459
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.20
    0.08
    575
    +0.16
    0.07
    415
    +0.15
    0.05
    Negative Logits
     ?)
    -0.60
    )?
    -0.59
     meanwhile
    -0.56
    zbollah
    -0.55
    also
    -0.55
     2018
    -0.54
    etheless
    -0.53
     Strategies
    -0.52
     Pearce
    -0.52
    cipled
    -0.52
    POSITIVE LOGITS
    âĢ¦.
    0.81
     whereas
    0.74
    .
    0.73
     haha
    0.73
     [âĢ¦]
    0.72
    âĢ¦..
    0.70
    ....
    0.69
     :(
    0.69
    âĢ¦."
    0.69
     [...]
    0.68
    Activations Density 0.670%

    No Known Activations