© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1490
    Prev
    Next
    INDEX
    Explanations

    proper names and titles 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.23
    1.1%
    5
    +0.11
    0.5%
    378
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.23
    0.06
    668
    +0.11
    0.05
    5
    +0.11
    0.05
    Negative Logits
    ©¶æ¥µ
    -0.68
    icter
    -0.68
    dozen
    -0.65
     tack
    -0.64
    oling
    -0.63
    ]."
    -0.63
    patch
    -0.61
    eled
    -0.60
    RL
    -0.60
    drive
    -0.59
    POSITIVE LOGITS
     specializes
    0.91
     refers
    0.88
     consists
    0.86
     strives
    0.85
     represents
    0.83
     embodies
    0.83
     is
    0.80
     aka
    0.79
     combines
    0.78
     writes
    0.77
    Activations Density 0.460%

    No Known Activations