© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    names and locations related to various events or enterprises

    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
    542
    +0.11
    0.5%
    213
    +0.10
    0.5%
    549
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    232
    +0.10
    0.01
    542
    +0.10
    0.01
    Negative Logits
     Rivals
    -0.66
     saline
    -0.63
    ãĥ¼ãĥĨ
    -0.61
     padd
    -0.61
    ************
    -0.61
    natureconservancy
    -0.60
     Socket
    -0.58
    inventoryQuantity
    -0.57
    âĸ¬âĸ¬
    -0.57
     Towns
    -0.57
    POSITIVE LOGITS
    uca
    1.15
    owitz
    1.07
    atile
    0.94
    ovie
    0.91
    ten
    0.85
    okia
    0.83
    osa
    0.83
    ocity
    0.82
    opa
    0.81
    owski
    0.81
    Activations Density 0.034%

    No Known Activations