© 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. 22534
    Prev
    Next
    INDEX
    Explanations

    detailed specifications and features of items or models

    oai_token-act-pair · gpt-4o-miniTriggered 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
    145
    +0.15
    0.7%
    508
    +0.10
    0.5%
    217
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.15
    0.04
    326
    +0.10
    0.05
    76
    +0.10
    0.04
    Negative Logits
    âĹ¼
    -0.71
    orsi
    -0.71
    notations
    -0.70
    another
    -0.64
    ãģĦ
    -0.63
    yet
    -0.62
    choes
    -0.61
     sugg
    -0.60
     behavi
    -0.60
     subsequ
    -0.59
    POSITIVE LOGITS
     Requires
    0.88
     /
    0.79
    ;
    0.78
     Includes
    0.77
     Description
    0.77
     Categories
    0.77
    ;;;;;;;;;;;;
    0.77
     Date
    0.76
     Avg
    0.75
     Required
    0.75
    Activations Density 0.269%

    No Known Activations