© 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 12288
    9. 8-RES_FS12288-JB
    11. 10641
    Prev
    Next
    INDEX
    Explanations

    perspectives and reflections on personal growth, self-awareness, and understanding others

    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
    416
    +0.11
    0.5%
    215
    +0.10
    0.4%
    618
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.06
    29
    +0.10
    0.05
    192
    +0.10
    0.04
    Negative Logits
    yss
    -0.75
    ando
    -0.63
     stip
    -0.58
    ploy
    -0.58
     facult
    -0.58
    merce
    -0.57
    theless
    -0.57
    erto
    -0.57
    quit
    -0.57
     deletion
    -0.57
    POSITIVE LOGITS
     microscope
    1.04
     afar
    1.00
     hindsight
    0.97
     objectively
    0.94
     firsthand
    0.88
     microsc
    0.86
     replay
    0.83
     prism
    0.83
     lens
    0.82
    MRI
    0.81
    Activations Density 0.654%

    No Known Activations