© 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. 10393
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    481
    +0.14
    0.6%
    306
    +0.13
    0.6%
    314
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.14
    0.04
    195
    +0.13
    0.02
    31
    +0.12
    0.04
    Negative Logits
     Palestin
    -0.72
     suspic
    -0.66
     surv
    -0.62
     Maver
    -0.62
    peak
    -0.61
     therap
    -0.61
     territ
    -0.58
     Trail
    -0.58
     Vaugh
    -0.58
     unnecess
    -0.57
    POSITIVE LOGITS
    ables
    1.03
    able
    1.01
    backs
    0.89
    eth
    0.89
    ings
    0.87
    rers
    0.83
    ible
    0.80
    wolves
    0.79
    gal
    0.77
    ingly
    0.77
    Activations Density 0.346%

    No Known Activations