© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    locations and geographical information

    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
    480
    +0.58
    3.4%
    447
    +0.22
    1.3%
    87
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.58
    0.04
    266
    +0.22
    0.13
    288
    +0.17
    0.16
    Negative Logits
    ĪĴ
    -0.56
    OULD
    -0.46
    vae
    -0.45
    ļé
    -0.45
    rive
    -0.45
    -)
    -0.45
    çīĪ
    -0.43
    pload
    -0.43
    encer
    -0.42
    essor
    -0.41
    POSITIVE LOGITS
     whereas
    0.79
    .
    0.78
    ;
    0.76
     because
    0.75
    ,[
    0.73
    .[
    0.70
     unless
    0.69
     insofar
    0.67
     but
    0.67
     except
    0.64
    Activations Density 1.828%

    No Known Activations