© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 13544
    Prev
    Next
    INDEX
    Explanations

    comparative words related to quantity or degree

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    389
    +0.12
    0.5%
    455
    +0.11
    0.5%
    191
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.12
    0.04
    455
    +0.11
    0.04
    226
    +0.11
    0.03
    Negative Logits
     Unlock
    -0.71
     Enhancement
    -0.67
    Ds
    -0.67
    DK
    -0.66
    oÄŁ
    -0.62
     Advis
    -0.61
     Events
    -0.61
    å¯
    -0.61
    de
    -0.61
     Unlimited
    -0.61
    POSITIVE LOGITS
     than
    1.23
    ened
    1.16
    ening
    1.08
     forgiving
    0.89
    ens
    0.86
     fortunate
    0.80
     glamorous
    0.79
     inclined
    0.78
     stringent
    0.78
     conspicuous
    0.75
    Activations Density 0.040%

    No Known Activations