© 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 24576
    9. 8-RES_FS24576-JB
    11. 12002
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical procedures or investigations

    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
    480
    +0.48
    2.4%
    752
    +0.12
    0.6%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.01
    266
    +0.12
    0.09
    752
    +0.10
    0.07
    Negative Logits
     himself
    -0.56
     lux
    -0.53
     airs
    -0.52
    csv
    -0.52
     afar
    -0.52
    66666666
    -0.51
    ++;
    -0.51
     Emin
    -0.51
     Valhalla
    -0.50
     XXX
    -0.50
    POSITIVE LOGITS
     regarding
    0.96
     concerning
    0.84
     authorizing
    0.82
     recommending
    0.77
     urging
    0.77
    uggest
    0.72
     relating
    0.72
     awarding
    0.72
     Regarding
    0.70
    cerning
    0.69
    Activations Density 1.057%

    No Known Activations