© 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. 9449
    Prev
    Next
    INDEX
    Explanations

    words related to possibilities and opportunities

    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
    520
    +0.12
    0.6%
    105
    +0.12
    0.5%
    752
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.12
    0.05
    520
    +0.12
    0.04
    737
    +0.11
    0.04
    Negative Logits
     portraits
    -0.61
    Edited
    -0.60
    rodu
    -0.59
     soaked
    -0.58
    igl
    -0.58
    ashtra
    -0.58
     recap
    -0.57
     waves
    -0.57
     shocks
    -0.56
     pulp
    -0.56
    POSITIVE LOGITS
     limitless
    0.73
    izons
    0.71
    chance
    0.67
    oso
    0.65
    btn
    0.65
    ecided
    0.64
    foreseen
    0.64
    aido
    0.64
     unlimited
    0.62
    forge
    0.62
    Activations Density 0.634%

    No Known Activations