© 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 3072
    9. 8-RES_FS3072-JB
    11. 254
    Prev
    Next
    INDEX
    Explanations

    the names of specific individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    659
    +0.20
    0.9%
    511
    +0.11
    0.5%
    525
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.20
    232
    +0.11
    0.11
    511
    +0.10
    0.11
    Negative Logits
    ModLoader
    -0.89
    âĶĢâĶĢ
    -0.86
     Emblem
    -0.70
     Confederation
    -0.70
     Mae
    -0.67
    etheless
    -0.67
     Fancy
    -0.66
    姫
    -0.66
     Indo
    -0.64
     Georgian
    -0.64
    POSITIVE LOGITS
    linger
    0.99
    aney
    0.98
    onson
    0.96
    isner
    0.95
    antz
    0.94
    anson
    0.93
    lett
    0.93
    inski
    0.90
    zinski
    0.89
    enson
    0.88
    Activations Density 0.671%

    No Known Activations