© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 24576
    5. 8-RES_FS24576-JB
    6. 10177
    Prev
    Next
    INDEX
    Explanations

    unemployment and economic indicators

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    709
    +0.13
    0.6%
    761
    +0.12
    0.5%
    368
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    439
    +0.13
    0.04
    368
    +0.12
    0.03
    307
    +0.11
    0.03
    Negative Logits
    sbm
    -0.75
    wcsstore
    -0.72
    soDeliveryDate
    -0.70
    Pic
    -0.69
    é¾įåĸļ士
    -0.69
    å§«
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    ãĥĥãĥĪ
    -0.66
    IRT
    -0.65
    etch
    -0.64
    POSITIVE LOGITS
     (%
    0.87
     (%)
    0.83
     (-
    0.83
     statistic
    0.82
     (.
    0.82
     nationally
    0.81
     (âĪĴ
    0.77
     ratio
    0.77
     (<
    0.75
     Adjusted
    0.74
    Activations Density 0.066%

    No Known Activations