© 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. 8051
    Prev
    Next
    INDEX
    Explanations

    updates and news items

    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
    274
    +0.11
    0.5%
    487
    +0.11
    0.5%
    195
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.11
    0.02
    274
    +0.11
    0.02
    296
    +0.11
    0.02
    Negative Logits
    aden
    -0.91
    gravity
    -0.82
    athered
    -0.80
    anship
    -0.78
    enic
    -0.78
    uman
    -0.74
    wegian
    -0.73
    stood
    -0.71
    vasive
    -0.70
    atom
    -0.69
    POSITIVE LOGITS
     UPDATE
    1.05
     Update
    1.05
    UPDATE
    0.99
    Update
    0.94
    :]
    0.93
     Sources
    0.85
     EDIT
    0.83
    :
    0.82
     update
    0.81
     III
    0.79
    Activations Density 0.021%

    No Known Activations